# RunLocalAI — full content index

> Complete machine-readable index of RunLocalAI: every indexable model page,
> hardware verdict, tool review, guide, course, glossary term, and error fix.
> The curated summary lives at https://www.runlocalai.co/llms.txt.

Editorial standards, benchmark sourcing, and methodology:
- [Editorial policy](https://www.runlocalai.co/editorial-policy)
- [Methodology](https://www.runlocalai.co/methodology)
- [Will-It-Run framework](https://www.runlocalai.co/resources/will-it-run-framework)

Machine-readable endpoints:
- [Sitemap](https://www.runlocalai.co/sitemap.xml)
- [RSS feed — recently updated pages](https://www.runlocalai.co/feed.xml)
- [Datasets](https://www.runlocalai.co/datasets)

## Models (195)
- [Aya 23 35B](https://www.runlocalai.co/models/aya-23-35b): Aya 23 at 35B. Built on Cohere's Command-R lineage. Non-commercial.
- [Aya 23 8B](https://www.runlocalai.co/models/aya-23-8b): Cohere's multilingual research model covering 23 languages. CC-BY-NC — research only.
- [Aya Expanse 32B](https://www.runlocalai.co/models/aya-expanse-32b): Cohere's multilingual Aya at 32B. Covers 23 languages; strongest open-weight multilingual model in late 2024 — Apache-2.0 alternative is Qwen 2.5 32B but Aya has deeper coverage o…
- [Baichuan 4 13B](https://www.runlocalai.co/models/baichuan-4-13b): Baichuan AI's 13B. Chinese-language ecosystem alternative to Qwen / GLM. Restricted commercial license.
- [BGE M3](https://www.runlocalai.co/models/bge-m3): BAAI's multilingual embedding flagship. Dense + sparse + ColBERT-style multi-vector. The de-facto open multilingual embedding pick.
- [CodeGemma 7B](https://www.runlocalai.co/models/codegemma-7b): Coding-specialist Gemma. Decent FIM completion. Now mostly historical with Qwen 2.5 Coder dominating.
- [CodeQwen 1.5 7B](https://www.runlocalai.co/models/codeqwen-1.5-7b): CodeQwen 1.5 — Qwen Coder predecessor. Superseded by Qwen 2.5 Coder for new deployments.
- [Codestral 22B](https://www.runlocalai.co/models/codestral-22b): Mistral's coding-specialist. Strong fill-in-the-middle for IDE autocompletion. Personal/research use only.
- [Codestral Mamba 7B](https://www.runlocalai.co/models/codestral-mamba-7b): Mistral's Mamba (state-space) architecture coding model. Linear inference cost — the architectural alternative to attention-based coding models. Apache 2.0.
- [Command R 35B](https://www.runlocalai.co/models/command-r-35b): Cohere's mid-tier — RAG and tool use. Non-commercial license.
- [Command R+ (Aug 2024)](https://www.runlocalai.co/models/command-r-plus-08-2024): Cohere's August 2024 Command R+ refresh. RAG-optimized; non-commercial license. Strong tool-calling and citation discipline.
- [Command R+ 104B](https://www.runlocalai.co/models/command-r-plus-104b): Cohere's flagship — RAG-tuned, multilingual. Open weights but non-commercial.
- [DBRX Base](https://www.runlocalai.co/models/dbrx-base): DBRX base (non-instruct). 132B total / 36B active fine-grained MoE.
- [DBRX Instruct](https://www.runlocalai.co/models/dbrx-instruct): Databricks' MoE. 132B total / 36B active. Designed for Mosaic ML pipelines; strong tool-calling discipline. Multi-GPU only.
- [DeepSeek Coder V2 236B](https://www.runlocalai.co/models/deepseek-coder-v2-236b): Full DeepSeek Coder V2. 236B total / 21B active MoE coder.
- [DeepSeek Coder V2 Lite (16B)](https://www.runlocalai.co/models/deepseek-coder-v2-lite): MoE coding specialist — 16B total / 2.4B active. Fast on 12GB cards.
- [DeepSeek Coder V3](https://www.runlocalai.co/models/deepseek-coder-v3): DeepSeek's coder line successor. Dense 33B; competitive with Qwen 2.5 Coder 32B on SWE-Bench.
- [DeepSeek MoE 16B Base](https://www.runlocalai.co/models/deepseek-moe-16b-base): DeepSeek's first MoE — 16B / 2.4B active. Older model retained for ecosystem-context value as the base of the V2/V3 lineage.
- [DeepSeek R1 (671B reasoning)](https://www.runlocalai.co/models/deepseek-r1): Open reasoning model that closed the gap with frontier proprietary reasoners. Visible chain-of-thought, MIT license, and a family of distilled smaller variants.
- [DeepSeek R1 Distill Llama 70B](https://www.runlocalai.co/models/deepseek-r1-distill-llama-70b): Reasoning distillation onto Llama 3.3 70B. Best-in-class open-weight reasoner you can actually fit on a workstation.
- [DeepSeek R1 Distill Llama 8B](https://www.runlocalai.co/models/deepseek-r1-distill-llama-8b): R1 reasoning distilled into a Llama 3 8B base. Smaller R1 distill; useful when 32B is too heavy. Reasoning quality is meaningfully below the 32B distill but still beats non-reason…
- [DeepSeek R1 Distill Mistral 24B](https://www.runlocalai.co/models/deepseek-r1-distill-mistral-24b): Community R1 distill onto a Mistral Small 3 base. Apache 2.0; combines R1 reasoning with Mistral instruction polish.
- [DeepSeek R1 Distill Qwen 1.5B](https://www.runlocalai.co/models/deepseek-r1-distill-qwen-1.5b): Smallest R1 distill. Surprisingly capable reasoning at 1.5B for its size class; right pick when you need reasoning AND edge deployment.
- [DeepSeek R1 Distill Qwen 14B](https://www.runlocalai.co/models/deepseek-r1-distill-qwen-14b): 14B reasoning distill. Fits on 12GB cards.
- [DeepSeek R1 Distill Qwen 3 32B](https://www.runlocalai.co/models/deepseek-r1-distill-qwen-3-32b): Newer R1 distill on a Qwen 3 base. Combines R1 reasoning with Qwen 3's reasoning-toggle architecture. Apache 2.0.
- [DeepSeek R1 Distill Qwen 32B](https://www.runlocalai.co/models/deepseek-r1-distill-qwen-32b): 32B distill — fits on a single 24GB card with reasoning capability. Best price-per-thinking-token combo for prosumers.
- [DeepSeek R1 Distill Qwen 7B](https://www.runlocalai.co/models/deepseek-r1-distill-qwen-7b): Smallest practical R1 distill. Reasoning on a 6GB GPU.
- [DeepSeek V2.5 236B](https://www.runlocalai.co/models/deepseek-v2.5-236b): DeepSeek V2.5 — merged V2 chat + Coder. Pre-V3 baseline; 21B active MoE.
- [DeepSeek V3 (671B MoE)](https://www.runlocalai.co/models/deepseek-v3): DeepSeek's flagship MoE — 671B total / 37B active. Server-tier, but the smaller R1 distills make this lineage approachable.
- [DeepSeek V3 Lite (16B MoE)](https://www.runlocalai.co/models/deepseek-v3-lite): Distillation of DeepSeek V3 to a smaller MoE. 16B total / 2.4B active. Captures most of V3's reasoning at consumer-card-friendly memory.
- [DeepSeek V4](https://www.runlocalai.co/models/deepseek-v4): DeepSeek's spring 2026 frontier MoE. 745B total / 38B active. The current open-weight benchmark leader on coding + math; closes the gap with closed-source flagships on reasoning.
- [DeepSeek V4 Flash (284B MoE)](https://www.runlocalai.co/models/deepseek-v4-flash): The cost-efficient sibling of V4-Pro. 284B total / 13B active MoE, same hybrid CSA+HCA attention, same 1M context. The MoE active-param ratio (4.5%) makes it surprisingly fast for…
- [DeepSeek V4 Pro (1.6T MoE)](https://www.runlocalai.co/models/deepseek-v4-pro): DeepSeek's April 2026 frontier flagship. 1.6T total / 49B active MoE with hybrid Compressed Sparse Attention + Heavily Compressed Attention. 1M context window. Closes most of the…
- [Devstral Small 2 24B](https://www.runlocalai.co/models/devstral-small-2-24b): Mistral's coding-specialized Mistral Small 2 successor. Apache 2.0 — the rare commercial-OK Mistral coder.
- [Dolphin 3.0 Llama 3.2 3B](https://www.runlocalai.co/models/dolphin-3-llama-3.2-3b): Eric Hartford's Dolphin fine-tune at 3B. Less-censored than the base Llama; popular for unconstrained-generation use cases.
- [Dolphin 3 Llama 3.3 70B](https://www.runlocalai.co/models/dolphin-3-llama-3.3-70b): Eric Hartford's Dolphin 3 at 70B Llama 3.3 base. Less-restricted alternative for creative / unconstrained workflows.
- [Dolphin 3.0 Mistral 24B](https://www.runlocalai.co/models/dolphin-3.0-mistral-24b): Eric Hartford's Dolphin fine-tune of Mistral Small 3 — uncensored, function-calling, agent-friendly.
- [EVA Llama 3.3 70B](https://www.runlocalai.co/models/eva-llama-3.3-70b): EVA community's storytelling-focused fine-tune of Llama 3.3 70B. Popular in the creative-writing / roleplay community.
- [EXAONE 3.5 2.4B](https://www.runlocalai.co/models/exaone-3.5-2.4b): LG AI's edge-tier EXAONE. Strong Korean / English. Research-only license.
- [EXAONE 3.5 32B](https://www.runlocalai.co/models/exaone-3.5-32b): LG AI Research's flagship Korean-ecosystem model. Strong on Korean/Japanese language tasks; competitive on English. License blocks commercial use without LG agreement.
- [EXAONE 3.5 8B](https://www.runlocalai.co/models/exaone-3.5-8b): Smaller EXAONE for consumer-tier Korean / CJK workloads.
- [Falcon 3 10B](https://www.runlocalai.co/models/falcon-3-10b): TII's Falcon 3 at the 10B tier. Strong on Arabic-language tasks; competitive on English.
- [Falcon 3 7B Instruct](https://www.runlocalai.co/models/falcon-3-7b): Falcon 3 mid-size from TII. Permissive Falcon license; multilingual focus.
- [Falcon Mamba 7B](https://www.runlocalai.co/models/falcon-mamba-7b): TII's Mamba (state-space) architecture model. Linear inference cost; the architectural alternative to attention-based models.
- [Gemma 2 9B Instruct](https://www.runlocalai.co/models/gemma-2-9b-it): Mid-size Gemma 2. Strong chat quality with a different training mix from Llama family.
- [Gemma 3 12B](https://www.runlocalai.co/models/gemma-3-12b): 12B Gemma 3. Fits on 12GB consumer cards. Multimodal.
- [Gemma 3 1B](https://www.runlocalai.co/models/gemma-3-1b): Smallest text-only Gemma 3 for phones and IoT.
- [Gemma 3 27B](https://www.runlocalai.co/models/gemma-3-27b): Pre-Gemma-4 flagship. Multimodal (4B+ variants), 128K context, 140 languages. Strong daily driver on 24GB cards.
- [Gemma 3 4B](https://www.runlocalai.co/models/gemma-3-4b): 4B Gemma 3 for edge. Multimodal.
- [Gemma 4 26B MoE](https://www.runlocalai.co/models/gemma-4-26b-moe): MoE variant of Gemma 4. Faster per-token than the 31B dense at similar quality on most tasks.
- [Gemma 4 31B Dense](https://www.runlocalai.co/models/gemma-4-31b): Google's flagship dense Gemma 4. Beats some 400B-class proprietary models on benchmarks. Targets the 24GB single-GPU sweet spot.
- [Gemma 4 E2B (Effective 2B)](https://www.runlocalai.co/models/gemma-4-e2b): Smallest Gemma 4. Designed for phones and Raspberry-Pi-class hardware.
- [Gemma 4 E4B (Effective 4B)](https://www.runlocalai.co/models/gemma-4-e4b): Edge-class Gemma 4. The 'Effective 4B' branding signals it punches above its parameter count via training-data quality.
- [GLM-4 9B](https://www.runlocalai.co/models/glm-4-9b): Zhipu's GLM-4 at 9B. Strong on Chinese-language tasks; tool-calling format slightly different from OpenAI convention.
- [GLM-4V 9B](https://www.runlocalai.co/models/glm-4v-9b): GLM-4 with vision encoder. Strong on Chinese document Q&A; restricted commercial license.
- [GLM-5](https://www.runlocalai.co/models/glm-5): Zhipu's GLM-5 currently leads the Open LLM Leaderboard 2026. Strong reasoning and bilingual EN/ZH capability.
- [GLM-5 Pro](https://www.runlocalai.co/models/glm-5-pro): Zhipu's GLM-5 flagship. 144B total / 16B active MoE. Strong on Chinese-language tasks; competitive on English at the workstation-cluster tier.
- [GLM-5.2](https://www.runlocalai.co/models/glm-5.2): GLM-5.2 is Zhipu AI's (Z.ai) flagship open-weight LLM, released on Hugging Face as zai-org/GLM-5.2 (2026-06). It is a Mixture-of-Experts decoder-only transformer with a new "Index…
- [Granite 3 MoE (3B active)](https://www.runlocalai.co/models/granite-3-moe-3b-active): Granite MoE shape. 16B total / 3B active. Workstation-deployable; the IBM enterprise alternative to Qwen / DeepSeek small MoEs.
- [Granite 3.0 2B Instruct](https://www.runlocalai.co/models/granite-3.0-2b): IBM Granite at 2B. Apache 2.0 enterprise-friendly small model with safety tuning.
- [Granite 3.0 8B Instruct](https://www.runlocalai.co/models/granite-3.0-8b): Granite 3.0 8B — IBM's enterprise-tier baseline. Apache 2.0.
- [Granite 3.2 8B](https://www.runlocalai.co/models/granite-3.2-8b): IBM's enterprise-tuned 8B. Apache 2.0. Strong on enterprise-shaped tool-calling and structured output. Watson + RHEL ecosystem alignment.
- [Granite 3.3 8B](https://www.runlocalai.co/models/granite-3.3-8b): IBM Granite 3.3. Iterative refresh of 3.2 — same architecture; improved instruction following and tool-call reliability. Apache 2.0.
- [Granite 4.1 30B Instruct](https://www.runlocalai.co/models/granite-4.1-30b-instruct): Granite 4.1 30B Instruct is the largest Granite 4.1 language model: a dense, decoder-only transformer with 28.9B parameters across 64 layers (grouped-query attention, RoPE, SwiGLU…
- [Granite 4.1 3B Instruct](https://www.runlocalai.co/models/granite-4.1-3b-instruct): Granite 4.1 3B Instruct is the smallest of IBM's Granite 4.1 language models, released April 29, 2026 under Apache 2.0. It is a dense, decoder-only transformer — 3.4B parameters,…
- [Granite 4.1 8B Instruct](https://www.runlocalai.co/models/granite-4.1-8b-instruct): Granite 4.1 8B Instruct is the mid-size model in IBM's Granite 4.1 family: a dense, decoder-only transformer with 8.79B parameters (40 layers, grouped-query attention, RoPE, SwiGL…
- [Hermes 3 Llama 3.1 70B](https://www.runlocalai.co/models/hermes-3-llama-3.1-70b): Hermes 3 at 70B. Workstation-tier agent-tuned model.
- [Hermes 3 Llama 3.1 8B](https://www.runlocalai.co/models/hermes-3-llama-3.1-8b): NousResearch's Hermes fine-tune of Llama 3.1 8B. Stronger system-prompt adherence, JSON output, role-play, and agent steering than the base Llama.
- [Hermes 3 Llama 3.2 3B](https://www.runlocalai.co/models/hermes-3-llama-3.2-3b): Nous Research's Hermes 3 fine-tune of Llama 3.2 3B. Strong general-instruction following at the 3B tier.
- [Hermes 4 Llama 3.3 70B](https://www.runlocalai.co/models/hermes-4-llama-3.3-70b): Nous Research's Hermes 4 fine-tune of Llama 3.3 70B. Strong on instruction following and creative tasks; community-favored alternative to base Llama.
- [Hunyuan 3.0 (Hy3)](https://www.runlocalai.co/models/hunyuan-3.0): Hy3 is Tencent's flagship open-weights release: a 295B-parameter Mixture-of-Experts text model activating 21B parameters per token, plus a 3.8B-parameter multi-token-prediction (M…
- [Hunyuan Large 389B MoE](https://www.runlocalai.co/models/hunyuan-large-moe): Tencent's frontier MoE. 389B total / 52B active. License permits commercial use with restrictions on companies above MAU thresholds.
- [InternLM 2.5 7B Chat](https://www.runlocalai.co/models/internlm-2.5-7b-chat): InternLM 2.5 mid-size chat. Apache 2.0; strong on math and Chinese.
- [InternLM 3 8B](https://www.runlocalai.co/models/internlm-3-8b): Shanghai AI Lab's open-research line. InternLM 3 at 8B; strong on Chinese-language tasks.
- [InternVL 2.5 26B](https://www.runlocalai.co/models/internvl-2.5-26b): InternVL 2.5 mid-tier — Shanghai AI Lab vision-language model with strong document and chart understanding.
- [InternVL 2.5 78B](https://www.runlocalai.co/models/internvl-2.5-78b): InternVL 2.5 flagship. Approaches frontier proprietary VLMs on document and OCR tasks.
- [Jamba 1.5 Large](https://www.runlocalai.co/models/jamba-1.5-large): Jamba flagship at 398B total / 94B active. Frontier hybrid-architecture model with 256k context.
- [Jamba 1.5 Mini](https://www.runlocalai.co/models/jamba-1.5-mini): AI21's hybrid Mamba-Transformer MoE. 256k context with the SSM throughput advantage.
- [Janus-Pro 7B](https://www.runlocalai.co/models/janus-pro-7b): DeepSeek's multimodal 7B. Decoupled visual encoding for understanding vs generation — different from typical VLM design.
- [Kimi K1.5](https://www.runlocalai.co/models/kimi-k1.5): Moonshot's reasoning model. Reasoning-token emission with very long thinking-block depth — sometimes 5000+ tokens per query. Strong on math; restricted commercial license.
- [Kimi K2.6](https://www.runlocalai.co/models/kimi-k2.6): Moonshot's long-context, agent-oriented MoE. Optimized for stability under tool use and multi-step coding/planning workflows.
- [Kimi K2.7-Code](https://www.runlocalai.co/models/kimi-k2.7-code): Kimi K2.7-Code is a coding-specialized open-weight Mixture-of-Experts model from Moonshot AI (Hugging Face moonshotai/Kimi-K2.7-Code, 2026-06), built on K2.6 with ~1T total / ~32B…
- [LFM2.5-230M](https://www.runlocalai.co/models/lfm2.5-230m): LFM2.5-230M is Liquid AI's smallest LFM2.5 model: a 230M-parameter, text-only hybrid (14 layers — 8 double-gated LIV convolution blocks plus 6 GQA attention blocks) trained on a 1…
- [Llama 3.1 70B Instruct](https://www.runlocalai.co/models/llama-3.1-70b-instruct): The 70B sibling of Llama 3.1 8B. Strong generalist reasoning with 128K context, popular base for agentic fine-tunes (Hermes 3, Nemotron). Mostly superseded by Llama 3.3 70B for ne…
- [Llama 3.1 8B Instruct](https://www.runlocalai.co/models/llama-3.1-8b-instruct): Meta's small flagship. Strong general reasoning, 128K context, broad multilingual. The default first try for most local-AI use cases on consumer hardware.
- [Llama 3.1 Nemotron 70B Instruct](https://www.runlocalai.co/models/llama-3.1-nemotron-70b-instruct): NVIDIA's HelpSteer2-tuned Llama 3.1 70B. Topped Arena Hard at release. The pre-Nemotron-3 NVIDIA reference open weights.
- [Llama 3.1 Nemotron Nano 8B](https://www.runlocalai.co/models/llama-3.1-nemotron-nano-8b): Smallest of the Nemotron reasoning trio. NAS-optimized for inference efficiency on RTX hardware.
- [Llama 3.1 Nemotron Ultra 253B](https://www.runlocalai.co/models/llama-3.1-nemotron-ultra-253b): NVIDIA's top open reasoning model in the Llama 3.1 lineage. Server-tier; trained for groundbreaking reasoning accuracy on agentic workloads.
- [Llama 3.2 11B Vision](https://www.runlocalai.co/models/llama-3.2-11b-vision): Llama 3.2 multimodal at 11B. Consumer-tier multimodal predecessor to Llama 4 Scout.
- [Llama 3.2 11B Vision Instruct](https://www.runlocalai.co/models/llama-3.2-11b-vision-instruct): First-party multimodal Llama. Accepts images alongside text for VQA, document understanding, and chart reading. Runs on 12GB+ VRAM.
- [Llama 3.2 1B Instruct](https://www.runlocalai.co/models/llama-3.2-1b-instruct): True edge-tier Llama. Runs on a phone or Raspberry Pi. Useful for classification, simple summarization, and on-device agents.
- [Llama 3.2 3B Instruct](https://www.runlocalai.co/models/llama-3.2-3b-instruct): Lightweight 3B model for edge and laptop deployment. Check the quantized artifact and context against available memory. The earlier Apple Silicon speed estimate had no linked meas…
- [Llama 3.2 90B Vision](https://www.runlocalai.co/models/llama-3.2-90b-vision): Llama 3.2 multimodal at 90B. Datacenter-tier predecessor to Llama 4 Maverick. Strong visual reasoning.
- [Llama 3.2 90B Vision Instruct](https://www.runlocalai.co/models/llama-3.2-90b-vision-instruct): The 90B vision Llama. Best-in-class first-party multimodal open weight at the time of release. Workstation-class only.
- [Llama 3.3 70B Instruct](https://www.runlocalai.co/models/llama-3.3-70b-instruct): Late-2024 refresh of the 70B Llama line. Roughly matches Llama 3.1 405B on most benchmarks at one-fifth the parameter count. The default high-end model for serious local inference…
- [Llama 4 405B](https://www.runlocalai.co/models/llama-4-405b): Meta's dense flagship in the Llama 4 line. 405B params; comparable footprint to Llama 3.1 405B with the Llama 4 reasoning improvements.
- [Llama 4 70B](https://www.runlocalai.co/models/llama-4-70b): Llama 4 dense at 70B. Drop-in successor to Llama 3.3 70B; same hardware envelope, better on reasoning benchmarks.
- [Llama 4 Maverick](https://www.runlocalai.co/models/llama-4-maverick): Meta's high-end Llama 4 sibling — 128 experts MoE built for performance over efficiency. Multilingual strength is its standout. Effectively a server-tier model; consumer hardware…
- [Llama 4 Scout](https://www.runlocalai.co/models/llama-4-scout): Meta's 2026 flagship MoE model. 109B total parameters with only 17B active per forward pass and a record 10-million-token context window — unmatched in production at any tier. Bui…
- [LLaVA 1.6 Mistral 7B](https://www.runlocalai.co/models/llava-1.6-mistral-7b): LLaVA 1.6 on Mistral 7B base. Apache 2.0 vision-language with strong OCR.
- [LLaVA-OneVision 7B](https://www.runlocalai.co/models/llava-onevision-7b): LLaVA-OneVision unified single-image / multi-image / video VLM on Qwen 2 base.
- [LongCat-2.0](https://www.runlocalai.co/models/longcat-2.0): LongCat-2.0 is Meituan's 1.6-trillion-parameter MoE language model, activating ~48B parameters per token, released under MIT — announced June 30, 2026, with weights and inference…
- [Magistral 32B](https://www.runlocalai.co/models/magistral-32b): Mistral's reasoning-specialized fine-tune of a Mistral Small base. Reasoning-token emission similar to Qwen 3 / DeepSeek R1 in a smaller footprint. Research license — non-commerci…
- [MedGemma 27B](https://www.runlocalai.co/models/medgemma-27b): Medical-specialist Gemma fine-tune. Trained on de-identified medical literature and imaging. Research use under HAI-DEF terms.
- [MiniCPM 3 4B](https://www.runlocalai.co/models/minicpm-3-4b): OpenBMB's edge-optimized 4B. MIT license; designed for phone deployment. Strong reasoning per parameter.
- [MiniCPM-V 2.6 8B](https://www.runlocalai.co/models/minicpm-v-2.6-8b): Multimodal MiniCPM at 8B. Vision + text; strong on document Q&A for the size class.
- [MiniCPM-V 3 8B](https://www.runlocalai.co/models/minicpm-v-3-8b): MiniCPM-V successor. Multimodal at 8B with stronger document Q&A than 2.6.
- [MiniMax-M3](https://www.runlocalai.co/models/minimax-m3): MiniMax-M3 is a native multimodal Mixture-of-Experts model from MiniMax (Hugging Face MiniMaxAI/MiniMax-M3, 2026-06), with ~428B total / ~23B active parameters per token. It accep…
- [Ministral 3B Instruct](https://www.runlocalai.co/models/ministral-3b): Mistral edge model at 3B. Designed for on-device inference with extended 128k context. Research license only.
- [Ministral 8B Instruct](https://www.runlocalai.co/models/ministral-8b): Mistral 8B with sliding-window attention and 128k context. Research license — Mistral 7B v0.3 is the commercial alternative.
- [Mistral 7B Instruct v0.3](https://www.runlocalai.co/models/mistral-7b-instruct-v0.3): The reference 7B from Mistral. Apache 2.0 with native function calling. Mature ecosystem.
- [Mistral Large 2 (123B)](https://www.runlocalai.co/models/mistral-large-2): Mistral's flagship dense model. Open weights but restricted commercial license — research and non-commercial only.
- [Mistral Medium 3 24B (dense)](https://www.runlocalai.co/models/mistral-medium-3-24b): Dense variant in the Mistral Medium 3.5 family. Research license — non-commercial open. Same training data as the MoE flagship but in a smaller dense package.
- [Mistral Medium 3.5 (675B MoE)](https://www.runlocalai.co/models/mistral-medium-3.5): Mistral's April 2026 frontier MoE. 675B total / 41B active. Strong European-multilingual lineage carries through; the new release competes head-to-head with DeepSeek V4-Pro on mos…
- [Mistral Nemo 12B Instruct](https://www.runlocalai.co/models/mistral-nemo-12b): Joint Mistral/NVIDIA release with native 128K context and a new Tekken tokenizer. Strong multilingual; popular fine-tune base.
- [Mistral Saba 24B](https://www.runlocalai.co/models/mistral-saba-24b): Mistral's Arabic and South Asian language specialist at 24B. Research license.
- [Mistral Small 3 24B](https://www.runlocalai.co/models/mistral-small-3-24b): Re-release of Mistral Small under Apache 2.0. Competitive with Llama 3.3 70B at one-third the size for many tasks.
- [Mistral Small 3.2 24B](https://www.runlocalai.co/models/mistral-small-3.2-24b): Iterative refresh of Mistral Small 3 24B. Same architecture; improved instruction following and tool-call reliability. Apache 2.0.
- [Mixtral 8x22B Instruct](https://www.runlocalai.co/models/mixtral-8x22b-instruct): The bigger Mixtral. 141B total / 39B active. Strong general model, workstation-tier deployment.
- [Mixtral 8x7B Instruct](https://www.runlocalai.co/models/mixtral-8x7b-instruct): The MoE model that introduced the 8-experts pattern to the open-weight world. 47B params total, 13B active. Still a viable workhorse on 36GB+ setups.
- [Molmo 72B](https://www.runlocalai.co/models/molmo-72b): Molmo flagship. Apache 2.0 VLM rivaling proprietary models on UI pointing and visual reasoning.
- [Molmo 7B-D](https://www.runlocalai.co/models/molmo-7b-d): AI2's fully-open VLM. Trained on PixMo dataset; pointing capability for UI grounding.
- [Moondream 2](https://www.runlocalai.co/models/moondream-2): Tiny vision-language model. ~1.9B; designed for edge / embedded multimodal use cases. Apache 2.0.
- [Muse Glimmer 30B](https://www.runlocalai.co/models/muse-glimmer): Muse Glimmer 30B is Meta's first open agentic model, released 2026-08-10 under the Apache-2.0 license — a genuinely permissive, commercial-friendly license that's unusual for a fr…
- [Nemotron 3 Nano (30B-A3B)](https://www.runlocalai.co/models/nemotron-3-nano): NVIDIA's hybrid Mamba-2 + Transformer MoE for on-device agents. 30B total / 3B active. 1M-token context window with reasoning ON/OFF modes and 4× faster inference than the previou…
- [Nemotron 3 Nano 9B](https://www.runlocalai.co/models/nemotron-3-nano-9b): NVIDIA's Nemotron 3 at 9B. Tuned for NVIDIA-stack deployment patterns; strong tool-calling reliability.
- [Nemotron 3 Super (120B-A12B)](https://www.runlocalai.co/models/nemotron-3-super): Workstation-tier Nemotron 3. 120B total / 12B active. 5× higher throughput than the prior Super, 1M context, designed for multi-agent applications.
- [Nemotron 3 Super 49B](https://www.runlocalai.co/models/nemotron-3-super-49b): Nemotron 3 mid-tier. 49B dense; fits 32GB cards with AWQ. NVIDIA stack alignment carries through.
- [Nemotron 3 Ultra (550B-A55B)](https://www.runlocalai.co/models/nemotron-3-ultra): NVIDIA Nemotron 3 Ultra (550B-A55B) is a frontier-scale open-weight reasoning model from NVIDIA (Hugging Face nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, 2026-06), with 550B to…
- [Nemotron Mini 4B Instruct](https://www.runlocalai.co/models/nemotron-mini-4b): NVIDIA's edge-tier Nemotron. Distilled from Minitron lineage with role-play tuning.
- [NV-Embed v2](https://www.runlocalai.co/models/nv-embed-v2): NVIDIA's research-grade embedding model. Mistral-7B base. Top of MTEB at release.
- [OLMo 2 13B](https://www.runlocalai.co/models/olmo-2-13b): AI2's fully-open 13B. Apache 2.0; full training data + checkpoints + recipes published. The reproducibility-first model in the 13B class.
- [OLMo 2 32B](https://www.runlocalai.co/models/olmo-2-32b): Fully-open OLMo 2. AI2 publishes the full training data, code, and weights — the most reproducible 32B model.
- [OpenBioLLM Llama 3 70B](https://www.runlocalai.co/models/openbiollm-llama-3-70b): Medical / biomedical fine-tune of Llama 3 70B. Strong on USMLE and clinical-knowledge benchmarks; right pick when domain-specific medical depth matters more than general capabilit…
- [OpenCoder 8B](https://www.runlocalai.co/models/opencoder-8b): Fully-open coding model — training data + recipes published. Apache 2.0 with verifiable open-data lineage. The right pick for academic / reproducibility-sensitive work.
- [PaliGemma 2 10B](https://www.runlocalai.co/models/paligemma-2-10b): Mid-tier PaliGemma 2 fine-tuning base. Better baseline for complex vision tasks.
- [PaliGemma 2 3B](https://www.runlocalai.co/models/paligemma-2-3b): PaliGemma 2 — Gemma 2 base + SigLIP vision encoder. Designed for fine-tuning on specific vision tasks.
- [Phi-3.5 Mini Instruct](https://www.runlocalai.co/models/phi-3.5-mini-instruct): Compact 3.8B Phi for edge deployment. 128K context. Strong reasoning per parameter.
- [Phi-3.5 Vision](https://www.runlocalai.co/models/phi-3.5-vision): Multimodal Phi 3.5. Document and chart understanding at edge size. MIT licensed.
- [Phi-4 14B](https://www.runlocalai.co/models/phi-4-14b): Microsoft's Phi-4 14B trained on synthetic textbook-quality data. Punches above weight on reasoning and math; MIT licensed.
- [Phi-4 Mini 4B](https://www.runlocalai.co/models/phi-4-mini-4b): Microsoft's edge-tier Phi-4 variant. 3.8B params; designed for phone / tablet / Pi deployment. Strong reasoning per parameter — Phi family's traditional advantage carries to the s…
- [Phi-4 Multimodal](https://www.runlocalai.co/models/phi-4-multimodal): Multimodal variant of Phi-4 14B. Vision + text. Smaller than Llama 4 Scout but covers most image-Q&A workflows; right-sized for 16GB consumer cards.
- [Phi-4 Reasoning 14B](https://www.runlocalai.co/models/phi-4-reasoning-14b): Reasoning-focused fine-tune of Phi-4. Visible chain-of-thought, competitive with much larger models on math and STEM benchmarks.
- [Phi-4 Reasoning Mini 4B](https://www.runlocalai.co/models/phi-4-reasoning-mini-4b): Phi-4 reasoning at the edge tier. 3.8B with reasoning-token emission. The right pick when reasoning matters AND edge deployment is required.
- [Phind CodeLlama 34B v2](https://www.runlocalai.co/models/phind-codellama-34b-v2): Phind's CodeLlama-derived coder at 34B. Older release; retained for historical / continuity value. Newer Qwen Coder lineage has surpassed it.
- [Pixtral 12B](https://www.runlocalai.co/models/pixtral-12b): Mistral's multimodal entry. 12B parameters, vision + text, Apache 2.0. Good document and chart understanding.
- [Qwen 2-VL 7B](https://www.runlocalai.co/models/qwen-2-vl-7b): Qwen 2 vision-language predecessor to Qwen 2.5-VL. Apache 2.0 with strong document Q&A.
- [Qwen 2.5 0.5B Instruct](https://www.runlocalai.co/models/qwen-2.5-0.5b-instruct): Smallest Qwen 2.5. Apache 2.0; phone / Pi-class deployment target.
- [Qwen 2.5 1.5B Instruct](https://www.runlocalai.co/models/qwen-2.5-1.5b-instruct): Compact Qwen 2.5. The 1.5B Apache-2.0 baseline.
- [Qwen 2.5 14B Instruct](https://www.runlocalai.co/models/qwen-2.5-14b-instruct): 14B Qwen 2.5. Sweet spot for 16GB VRAM. Many production deployments still on this version.
- [Qwen 2.5 32B Instruct](https://www.runlocalai.co/models/qwen-2.5-32b-instruct): Dense 32B Qwen 2.5. Strong daily-driver on 24GB cards prior to Qwen 3 32B.
- [Qwen 2.5 3B Instruct](https://www.runlocalai.co/models/qwen-2.5-3b-instruct): Mid-edge Qwen 2.5. Note: 3B variant uses Qwen License (not Apache 2.0).
- [Qwen 2.5 72B Instruct](https://www.runlocalai.co/models/qwen-2.5-72b-instruct): The flagship of Qwen 2.5. Workstation-tier; needs 48GB+ VRAM for usable inference.
- [Qwen 2.5 7B Instruct](https://www.runlocalai.co/models/qwen-2.5-7b-instruct): The community-default small Qwen prior to Qwen 3. Still widely used because of mature ecosystem support.
- [Qwen 2.5 Coder 1.5B](https://www.runlocalai.co/models/qwen-2.5-coder-1.5b): Smallest Qwen 2.5 Coder. Targets edge / autocomplete on integrated GPUs and Apple Silicon laptops.
- [Qwen 2.5 Coder 14B Instruct](https://www.runlocalai.co/models/qwen-2.5-coder-14b-instruct): Coding-specialized Qwen 2.5 at 14B. The 16GB-VRAM tier coding model — fits comfortably with 8K context.
- [Qwen 2.5 Coder 32B Instruct](https://www.runlocalai.co/models/qwen-2.5-coder-32b-instruct): Coding-specialist Qwen 2.5. Beats GPT-4o on HumanEval and matches Sonnet on many code-edit benchmarks. The default local-coding model on 24GB cards.
- [Qwen 2.5 Coder 3B](https://www.runlocalai.co/models/qwen-2.5-coder-3b): Compact Qwen 2.5 Coder. Sweet spot for laptop autocomplete and small refactor agents.
- [Qwen 2.5 Coder 7B Instruct](https://www.runlocalai.co/models/qwen-2.5-coder-7b-instruct): Coding-specialized Qwen 2.5 at 7B. The 8-12GB-VRAM coding model — entry-tier autocomplete + IDE assistant. Smaller sibling of the 14B / 32B Coder line.
- [Qwen 2.5 Math 72B](https://www.runlocalai.co/models/qwen-2.5-math-72b): Largest Qwen 2.5 Math. Datacenter-tier math specialist; eclipsed by R1 distills for general reasoning.
- [Qwen 2.5 Math 7B](https://www.runlocalai.co/models/qwen-2.5-math-7b): Qwen 2.5 fine-tuned for math problem-solving with chain-of-thought and tool-integrated reasoning.
- [Qwen 2.5-VL 3B](https://www.runlocalai.co/models/qwen-2.5-vl-3b): Smallest Qwen 2.5-VL. Edge-deployable VLM with strong document Q&A.
- [Qwen 2.5-VL 72B](https://www.runlocalai.co/models/qwen-2.5-vl-72b): Qwen 2.5 vision-language flagship at 72B. Strong on document understanding + multi-image queries. Apache 2.0.
- [Qwen 2.5-VL 7B](https://www.runlocalai.co/models/qwen-2.5-vl-7b): Consumer-tier Qwen 2.5 VL. 7B + vision. Fits 8GB cards; the smallest practical multimodal Qwen.
- [Qwen 3 14B](https://www.runlocalai.co/models/qwen-3-14b): 14B Qwen 3. Fits on 12GB cards at Q4. Strong default for users with a single mid-range GPU.
- [Qwen 3 235B-A22B](https://www.runlocalai.co/models/qwen-3-235b-a22b): Qwen 3 flagship MoE. 235B total / 22B active per token, with built-in 'thinking' and 'non-thinking' modes that trade speed for reasoning depth at inference time. Best open-weight…
- [Qwen 3 30B-A3B](https://www.runlocalai.co/models/qwen-3-30b-a3b): Mid-tier Qwen 3 MoE. 30B total / 3B active means 70B-class quality at 7B-class inference speed on a single 24GB card. The sweet spot of the Qwen 3 lineup for prosumer hardware.
- [Qwen 3 32B](https://www.runlocalai.co/models/qwen-3-32b): Dense Qwen 3 32B. Best dense open-weight model in its size class at release; pairs nicely with a single RTX 5090 or 4090.
- [Qwen 3 4B](https://www.runlocalai.co/models/qwen-3-4b): Compact Qwen 3 for edge and laptop deployment. Outperforms many 7B models from prior generations.
- [Qwen 3.6 27B (MTP)](https://www.runlocalai.co/models/qwen-3-6-27b-mtp): Qwen 3.6 27B dense (not MoE) with Multi-Token Prediction. Sits between the 14B and 35B-A3B as a "single dense model with MTP throughput acceleration." Targets workloads where the…
- [Qwen 3.6 35B-A3B (MTP)](https://www.runlocalai.co/models/qwen-3-6-35b-a3b-mtp): Qwen 3.6 35B-A3B with Multi-Token Prediction (MTP). The "A3B" suffix means ~3B activated parameters per token via Mixture-of-Experts — inference cost stays mid-tier while total pa…
- [Qwen 3 7B](https://www.runlocalai.co/models/qwen-3-7b): Qwen 3 mid-tier. Same reasoning-mode toggle as Qwen 3 32B/14B/8B. Hits the consumer-laptop sweet spot.
- [Qwen 3 8B](https://www.runlocalai.co/models/qwen-3-8b): Qwen 3 at the 8B scale. Direct head-to-head against Llama 3.1 8B on most benchmarks; usually wins on coding and structured output.
- [Qwen 3 Coder 32B](https://www.runlocalai.co/models/qwen-3-coder-32b): Coding-specialized fine-tune of Qwen 3 32B. Curated coding corpus; outperforms Qwen 2.5 Coder 32B on SWE-Bench by ~6 points. Apache 2.0.
- [Qwen 3 Embedding 8B](https://www.runlocalai.co/models/qwen-3-embedding-8b): Qwen 3 family embedding model. Apache 2.0 with strong multilingual coverage.
- [Qwen 3.5 235B-A17B (MoE)](https://www.runlocalai.co/models/qwen-3.5-235b-a17b): Alibaba's May 2026 flagship. 397B total / 17B active MoE with hybrid thinking-mode toggle inherited from Qwen 3. Strongest open scientific reasoner per GPQA Diamond. The strongest…
- [QwQ 32B Preview](https://www.runlocalai.co/models/qwq-32b): Qwen team's reasoning-focused experimental release. Visible chain-of-thought in <think tags. Precursor to Qwen 3's thinking mode.
- [Ring-2.6-1T](https://www.runlocalai.co/models/ring-2-6-1t): InclusionAI's Ring-2.6-1T is a 1 trillion parameter Mixture-of-Experts model with ~32B activated parameters per token, released by Ant Group's AI research arm. Targets frontier re…
- [RWKV 7 'Goose' 1.5B](https://www.runlocalai.co/models/rwkv-7-1.5b): RWKV 7 'Goose' at 1.5B. Linear-time inference architecture (constant memory regardless of context). Apache 2.0.
- [SmolLM 2 1.7B Instruct](https://www.runlocalai.co/models/smollm-2-1.7b): SmolLM 2 flagship. Open data + open weights at the edge tier.
- [SmolLM 2 360M Instruct](https://www.runlocalai.co/models/smollm-2-360m): Hugging Face's SmolLM 2 at 360M. Apache 2.0; targets phone / Pi-class deployments.
- [SmolLM 3 3B](https://www.runlocalai.co/models/smollm-3-3b): HuggingFace's small-model line at 3B. Apache 2.0. Designed for edge / educational deployments.
- [Stable LM 2 12B](https://www.runlocalai.co/models/stablelm-2-12b): Stability AI's 12B. Stable LM line; commercial use requires paid membership. Solid baseline at 12B class.
- [StarCoder 2 15B](https://www.runlocalai.co/models/starcoder-2-15b): StarCoder 2 flagship. The largest BigCode coder; 16k context with strong fill-in-middle.
- [StarCoder 2 3B](https://www.runlocalai.co/models/starcoder-2-3b): BigCode's StarCoder 2 at 3B. Trained on The Stack v2 with 600+ programming languages.
- [StarCoder 2 7B](https://www.runlocalai.co/models/starcoder-2-7b): Mid-size StarCoder 2. The 8GB-VRAM autocomplete pick.
- [Step-3](https://www.runlocalai.co/models/step-3): StepFun's 1T-parameter MoE. 38B active. One of the largest open-weight models; cluster-only at any quant. Restricted license.
- [Tulu 3 70B](https://www.runlocalai.co/models/tulu-3-70b): Tulu 3 at 70B. AI2's fully-open instruct fine-tune — research transparency at scale.
- [Tulu 3 8B](https://www.runlocalai.co/models/tulu-3-8b): AI2's fully-open post-training recipe applied to Llama 3.1 8B. Open data, open code, open weights.
- [VibeThinker-3B](https://www.runlocalai.co/models/vibethinker-3b): VibeThinker-3B is a compact open-weight reasoning model from WeiboAI (Sina Weibo), fine-tuned from Qwen2.5-Coder-3B (Hugging Face WeiboAI/VibeThinker-3B, 2026-06). It is a dense ~…
- [Whisper Large v3](https://www.runlocalai.co/models/whisper-large-v3): OpenAI's flagship open speech-to-text model. 99 languages, MIT license. The de-facto open ASR baseline.
- [Whisper Large v3 Turbo](https://www.runlocalai.co/models/whisper-large-v3-turbo): Distilled Whisper Large v3. ~8x faster decode at near-equivalent accuracy on most languages.
- [WizardLM-2 8x22B](https://www.runlocalai.co/models/wizardlm-2-8x22b): Microsoft's RLHF-heavy fine-tune of Mixtral 8x22B. Briefly the top open chat model on LMSYS at release.
- [Yi 1.5 34B](https://www.runlocalai.co/models/yi-1.5-34b): 01.AI's 34B model. Solid bilingual EN/ZH performance, Apache 2.0.
- [Yi Coder 9B](https://www.runlocalai.co/models/yi-coder-9b): 01.AI's coding specialization at 9B. Apache 2.0; positioned as a lighter alternative to Qwen 2.5 Coder for the 16GB tier.

## Hardware (141)
- [AMD EPYC 9005 (Zen 5, Turin)](https://www.runlocalai.co/hardware/amd-epyc-9005): AMD's Zen 5 server CPU: up to 192 cores, 12-channel DDR5-6400 (~614 GB/s per socket), supporting terabyte-scale RAM. Anchors the CPU-inference strategy — running the full DeepSeek…
- [AMD Instinct MI210](https://www.runlocalai.co/hardware/amd-mi210): 64GB CDNA 2. Lower-power AMD datacenter option.
- [AMD Instinct MI250X](https://www.runlocalai.co/hardware/amd-mi250x): Previous-gen CDNA 2. 128GB HBM2e. Powered the Frontier supercomputer.
- [AMD Instinct MI300A (APU)](https://www.runlocalai.co/hardware/amd-mi300a): Combined CPU + GPU APU with 128GB unified HBM3. Powers the El Capitan supercomputer.
- [AMD Instinct MI300X](https://www.runlocalai.co/hardware/amd-mi300x): 192GB HBM3 datacenter card. Used by Microsoft, Oracle, Meta cloud deployments.
- [AMD Instinct MI325X](https://www.runlocalai.co/hardware/amd-mi325x): 256GB HBM3e — direct competitor to NVIDIA H200 with more memory.
- [AMD Instinct MI350X](https://www.runlocalai.co/hardware/amd-mi350x): The air-coolable sibling of the listed MI355X — same CDNA 4 silicon, 288GB HBM3E, ~8 TB/s, at a lower (~1,000W-class) power profile. The variant most non-hyperscale on-prem deploy…
- [AMD Instinct MI355X](https://www.runlocalai.co/hardware/amd-mi355x): Latest CDNA 4. 288GB HBM3e — currently the highest VRAM per chip on the market.
- [AMD Radeon RX 5600 XT](https://www.runlocalai.co/hardware/amd-rx-5600-xt): RDNA 1 mid-tier. 6 GB VRAM is the ceiling — fits 7B Q4 only with short context. No production ROCm support; Vulkan-only. ~20-30 tok/s on 7B Q4. The 'I have one in my 2020 build' a…
- [AMD Radeon RX 5700 XT](https://www.runlocalai.co/hardware/amd-rx-5700-xt): RDNA 1 flagship. ROCm support was always experimental and is effectively defunct in 2026. Vulkan via llama.cpp is the only operator-grade path; performance is bandwidth-OK but lac…
- [AMD Radeon RX 580 8GB](https://www.runlocalai.co/hardware/amd-rx-580): AMD Polaris with 8 GB VRAM. Cheap on used market ($70-100) but Polaris was dropped from ROCm in 2022, so AMD's official AI runtimes won't work. Vulkan via llama.cpp is the only pr…
- [AMD Radeon RX 6600](https://www.runlocalai.co/hardware/amd-rx-6600): Entry RDNA 2. 8 GB VRAM, lower bandwidth (224 GB/s) — the bottleneck on AI. ROCm officially supported on Linux. ~30-45 tok/s on 7B Q4. Reasonable budget AMD entry but bandwidth-li…
- [AMD Radeon RX 6600 XT](https://www.runlocalai.co/hardware/amd-rx-6600-xt): RDNA 2 mid-tier. 8 GB GDDR6 at 256 GB/s. ROCm officially supported on Linux. ~35-50 tok/s on 7B Q4. Bandwidth-bottlenecked vs the 6700 XT/6750 XT siblings. Reasonable AMD entry bu…
- [AMD Radeon RX 6650 XT](https://www.runlocalai.co/hardware/amd-rx-6650-xt): Refreshed 6600 XT with slightly faster GDDR6 (280 GB/s). 8 GB VRAM ceiling unchanged. ~40-55 tok/s on 7B Q4 with ROCm. Same buyer-decision shape as the 6600 XT — VRAM is the limit…
- [AMD Radeon RX 6700 XT](https://www.runlocalai.co/hardware/amd-rx-6700-xt): 12 GB RDNA 2 at the $280 used tier. ROCm officially supported. The VRAM headroom matters — fits 13B Q4 comfortably. ~50-65 tok/s on 7B Q4. Strong AMD value pick for the 'more VRAM…
- [AMD Radeon RX 6800](https://www.runlocalai.co/hardware/amd-rx-6800): 16 GB RDNA 2 — the AMD answer to the 4070 12 GB question. Comfortable for any 7B/13B model + 32B Q4 with offload. ROCm officially supported. ~70-90 tok/s on 7B Q4. The card to con…
- [AMD Radeon RX 6800 XT](https://www.runlocalai.co/hardware/amd-rx-6800-xt): RDNA 2 enthusiast. 16 GB VRAM, 512 GB/s bandwidth, more compute units than the base 6800. ROCm officially supported. ~85-110 tok/s on 7B Q4, 35-50 tok/s on 13B Q4. The peak of RDN…
- [AMD Radeon RX 6900 XT](https://www.runlocalai.co/hardware/amd-rx-6900-xt): RDNA 2 flagship. 16 GB VRAM at 512 GB/s, more compute than the 6800 XT. ROCm officially supported. ~95-130 tok/s on 7B Q4. The peak of RDNA 2 consumer AMD; used $450-550 in 2026.…
- [AMD Radeon RX 6950 XT](https://www.runlocalai.co/hardware/amd-rx-6950-xt): Refreshed 6900 XT with faster GDDR6 (576 GB/s). 16 GB VRAM, slightly more compute. ROCm officially supported. ~110-145 tok/s on 7B Q4. The bandwidth bump matters for inference; at…
- [AMD Radeon RX 7900 GRE](https://www.runlocalai.co/hardware/amd-rx-7900-gre): RDNA 3 'Golden Rabbit Edition' — 16 GB at 576 GB/s, between the 6800 XT and 7900 XT. ROCm officially supported. The current AMD value choice in the $500-600 tier. Comfortable for…
- [AMD Ryzen AI 9 HX 370 (Strix Point)](https://www.runlocalai.co/hardware/amd-ryzen-ai-9-hx-370): Strix Point laptop SoC. XDNA 2 NPU at 50 TOPS INT8 + RDNA 3.5 iGPU. ROCm support on Linux unlocks llama.cpp ROCm path; on Windows, ONNX Runtime + DirectML.
- [AMD Ryzen AI Halo](https://www.runlocalai.co/hardware/amd-ryzen-ai-halo): The Ryzen AI Halo is AMD's first-party answer to NVIDIA's DGX Spark: a 150 x 150 x 45.4 mm mini-workstation built on the Ryzen AI Max+ 395 (16 Zen 5 cores, Radeon 8060S with 40 RD…
- [Apple A17 Pro](https://www.runlocalai.co/hardware/apple-a17-pro): iPhone 15 Pro / 15 Pro Max SoC. 6-core CPU + 6-core GPU + 16-core Neural Engine (35 TOPS INT8). First A-series with hardware ray tracing; runs MLX-Swift and CoreML for on-device L…
- [Apple A18 Pro](https://www.runlocalai.co/hardware/apple-a18-pro): iPhone 16 Pro SoC. Improved Neural Engine for Apple Intelligence on-device workloads. 8GB RAM as the new mobile floor enables 3B-class on-device models.
- [Apple M1 Max](https://www.runlocalai.co/hardware/apple-m1-max): Original M1 Max. 400 GB/s. 32–64GB unified.
- [Apple M1 Ultra](https://www.runlocalai.co/hardware/apple-m1-ultra): Original Ultra — 800 GB/s. 64–128GB unified. Still capable for 70B Q4.
- [Apple M2 Max](https://www.runlocalai.co/hardware/apple-m2-max): M2 Max — 400 GB/s bandwidth, up to 96GB.
- [Apple M2 Ultra](https://www.runlocalai.co/hardware/apple-m2-ultra): M2 Ultra — up to 192GB at 800 GB/s. Mac Studio and Mac Pro hosting models.
- [Apple M3 Max](https://www.runlocalai.co/hardware/apple-m3-max): M3 Max — 400 GB/s bandwidth, up to 128GB.
- [Apple M3 Ultra](https://www.runlocalai.co/hardware/apple-m3-ultra): M3 Ultra — up to 512GB unified in Mac Studio top spec. 819 GB/s bandwidth.
- [Apple M4 (iPad Pro)](https://www.runlocalai.co/hardware/apple-m4-ipad): iPad Pro M4 — 10-core CPU + 10-core GPU + 16-core Neural Engine (38 TOPS). 8/16GB unified memory. Best mobile-class chip for local-AI experimentation as of 2026.
- [Apple M4 Max](https://www.runlocalai.co/hardware/apple-m4-max): M4 Max — 546 GB/s memory bandwidth, up to 128GB unified. Most capable laptop SoC for 70B+ models.
- [Apple M4 Pro](https://www.runlocalai.co/hardware/apple-m4-pro): Mid-tier M4 — 273 GB/s bandwidth, up to 48GB.
- [Apple M4 Ultra](https://www.runlocalai.co/hardware/apple-m4-ultra): Two-chip Ultra fusing two M4 Max dies. Up to 256GB unified memory at 1.1 TB/s. The single highest-VRAM consumer rig you can buy in a Mac Studio.
- [ASUS Ascent GX10 (NVIDIA GB10)](https://www.runlocalai.co/hardware/asus-ascent-gx10): The popular OEM twin of the NVIDIA DGX Spark, ~$1,000 cheaper (~$2,999). Same GB10 Grace Blackwell superchip, 128GB LPDDR5X unified, ~1 PFLOP FP4, ConnectX-7 for 2-node 256GB clus…
- [ASUS ROG Strix Scar 18 (RTX 5090 Mobile)](https://www.runlocalai.co/hardware/asus-rog-strix-scar-18): Desktop-replacement gaming/AI laptop with cooler thermals than ultraslims.
- [Framework Desktop (Ryzen AI Max+ 395)](https://www.runlocalai.co/hardware/framework-desktop-strix-halo): The enthusiast-favorite Strix Halo box: a Ryzen AI Max+ 395 system with 128GB LPDDR5X-8000 unified memory (~256 GB/s), up to ~96GB allocatable as VRAM on Linux. ~$1,999 DIY, open…
- [Framework Laptop 16 (RX 7700S)](https://www.runlocalai.co/hardware/framework-laptop-16): Modular AMD laptop. Limited GPU but the platform is the appeal.
- [GMKtec EVO-X2 (Ryzen AI Max+ 395)](https://www.runlocalai.co/hardware/gmktec-evo-x2): The cheapest mainstream 128GB Strix Halo mini-PC (~$1,499 entry). Ryzen AI Max+ 395, 128GB LPDDR5X-8000 unified, Radeon 8060S iGPU, up to ~96GB allocatable as VRAM. One of the mos…
- [GMKtec EVO-X3](https://www.runlocalai.co/hardware/gmktec-evo-x3): The EVO-X3 is GMKtec's second-generation Strix Halo mini-PC, launched globally on July 6, 2026 around the same Ryzen AI Max+ 395 (16 Zen 5 cores, Radeon 8060S, up to 126 platform…
- [Google Tensor G4](https://www.runlocalai.co/hardware/google-tensor-g4): Pixel 9 SoC. Google's mobile chip optimized for Gemini Nano + on-device transcription / summarization. NPU TOPS not publicly disclosed by Google; treat as on-par with mid-Snapdrag…
- [HP ZBook Ultra G1a (Ryzen AI Max+ PRO 395)](https://www.runlocalai.co/hardware/hp-zbook-ultra-g1a): The flagship Strix Halo mobile workstation: a 14" laptop with 128GB LPDDR5X-8000 unified memory (up to ~96GB allocatable to the Radeon 8060S iGPU). The portable form of the 128GB…
- [Intel Arc A770 16GB](https://www.runlocalai.co/hardware/intel-arc-a770-16gb): Alchemist 16GB. Cheapest path to that VRAM tier. Vulkan llama.cpp is the most-tested route.
- [Intel Arc B570](https://www.runlocalai.co/hardware/intel-arc-b570): 10GB Battlemage at sub-$220. Entry budget compute.
- [Intel Arc B580](https://www.runlocalai.co/hardware/intel-arc-b580): Battlemage architecture. 12GB at $250 — the budget compute card. IPEX-LLM and Vulkan are usable paths for AI.
- [Intel Arc Pro B60 24GB](https://www.runlocalai.co/hardware/intel-arc-pro-b60): Intel's workstation card explicitly marketed for low-cost local LLM inference. 24GB GDDR6, 456 GB/s, ~197 TOPS, ~$599. Board partners ship 48GB dual-GPU variants; Intel's 'Project…
- [Intel Core Ultra 300 (Panther Lake)](https://www.runlocalai.co/hardware/intel-core-ultra-300-panther-lake): Intel's current-gen AI-PC platform (launched Jan 2026, Intel 18A node), succeeding Lunar Lake. NPU5 delivers ~50 TOPS (clears the 40-TOPS Copilot+ bar); combined platform ~180 TOP…
- [Intel Gaudi 2](https://www.runlocalai.co/hardware/intel-gaudi-2): Previous-gen Habana accelerator. 96GB HBM2e.
- [Intel Gaudi 3](https://www.runlocalai.co/hardware/intel-gaudi-3): Intel's enterprise AI accelerator. 128GB HBM2e. Habana stack required — limited ecosystem support.
- [Intel Core Ultra 7 258V (Lunar Lake)](https://www.runlocalai.co/hardware/intel-lunar-lake-258v): Intel Lunar Lake 9-core. NPU 4 at 48 TOPS INT8 + Xe2 iGPU + Skymont E-cores. Copilot+ PC certified. Runs DirectML + ONNX Runtime + OpenVINO; primary on-device-AI Intel laptop chip…
- [Lenovo Legion 5 Pro Gen 7 (RTX 3080 16GB)](https://www.runlocalai.co/hardware/lenovo-legion-5-pro-gen-7): Ryzen 7 6800H + RTX 3080 16GB Mobile. The reference 'serious local-AI laptop' build. Look for the 16GB SKU.
- [Apple Mac Mini (M4)](https://www.runlocalai.co/hardware/mac-mini-m4): The cheapest entry into Apple unified memory and the most-recommended starter box for local AI. Base M4 with 16/24/32GB unified memory at 120 GB/s, in a tiny ~30-65W package. Runs…
- [Apple Mac Mini (M4 Pro)](https://www.runlocalai.co/hardware/mac-mini-m4-pro): The sweet-spot local-AI desktop for most people. M4 Pro with 24/48/64GB unified memory at 273 GB/s — more than double the base M4's bandwidth. A 64GB config runs 70B-class models…
- [Apple Mac Studio (M3 Ultra)](https://www.runlocalai.co/hardware/mac-studio-m3-ultra): Top-spec Mac Studio with M3 Ultra. Up to 512GB unified memory in custom configs.
- [Apple Mac Studio (M4 Max)](https://www.runlocalai.co/hardware/mac-studio-m4-max): The accessible Mac Studio tier, launched alongside the M3 Ultra. M4 Max with 36/48/64/96GB unified memory at 546 GB/s — about 2x the M4 Pro's bandwidth. The desk-side inference wo…
- [Apple MacBook Air (M4)](https://www.runlocalai.co/hardware/macbook-air-m4): The cheapest portable Apple unified-memory machine and a common 'try local LLMs on a laptop' entry point. M4 with 16/24/32GB at 120 GB/s, fanless. Runs 8-14B models well in bursts…
- [MacBook Pro 16" M4 Max](https://www.runlocalai.co/hardware/macbook-pro-16-m4-max): 16-inch M4 Max — 128GB unified at 546 GB/s. The most capable AI laptop in 2026.
- [NVIDIA A100 40GB](https://www.runlocalai.co/hardware/nvidia-a100-40gb): Original A100. 40GB HBM2 at 1.55 TB/s. Trained the early generation of frontier models.
- [NVIDIA A100 80GB SXM](https://www.runlocalai.co/hardware/nvidia-a100-80gb-sxm): Ampere datacenter flagship. 80GB HBM2e at 2 TB/s. Still common at cloud providers.
- [NVIDIA A40](https://www.runlocalai.co/hardware/nvidia-a40): Ampere workstation/datacenter hybrid. 48GB GDDR6.
- [NVIDIA B200](https://www.runlocalai.co/hardware/nvidia-b200): Datacenter Blackwell. 192GB HBM3e per chip, ~8 TB/s bandwidth. Cloud-tier — you rent these by the hour.
- [NVIDIA B300 (Blackwell Ultra)](https://www.runlocalai.co/hardware/nvidia-b300): The Blackwell Ultra datacenter refresh of the B200. 288GB HBM3e per GPU, ~8 TB/s, up to 1,400W; GB300 NVL72 racks reach 1.1 ExaFLOPS FP4. The current top-end reference for large-m…
- [NVIDIA DGX Spark (Project Digits)](https://www.runlocalai.co/hardware/nvidia-dgx-spark): NVIDIA's desktop AI box — Grace Blackwell GB10 with 128GB unified LPDDR5X. The closest consumer can get to running 200B-class models locally without renting cloud.
- [NVIDIA GB200 NVL72](https://www.runlocalai.co/hardware/nvidia-gb200-nvl72): 72-GPU Blackwell rack with 36 Grace CPUs. Hyperscale-only — relevant context here for understanding 'what frontier training runs on'.
- [NVIDIA GeForce GTX 1050 Ti](https://www.runlocalai.co/hardware/nvidia-gtx-1050-ti): Pascal-era entry GPU. 4 GB VRAM is the practical floor for any local model — fits 1-3B at Q4 with room for short context. CUDA-compatible but no FP16 acceleration on consumer Pasc…
- [NVIDIA GeForce GTX 1060 3GB](https://www.runlocalai.co/hardware/nvidia-gtx-1060-3gb): Pascal mid-range cut down to 3 GB VRAM. Below the practical AI floor — even 3B Q4 models need ~2 GB plus KV cache. Operators with this card almost universally pair it with CPU off…
- [NVIDIA GeForce GTX 1060 6GB](https://www.runlocalai.co/hardware/nvidia-gtx-1060-6gb): Pascal mid-range, 6 GB VRAM. The most-installed Steam GPU for many years; high probability the 'I have a GTX 1060' audience is asking about this card. Runs 7B Q4 models slowly (15…
- [NVIDIA GeForce GTX 1070](https://www.runlocalai.co/hardware/nvidia-gtx-1070): Pascal high-tier with 8 GB VRAM. Comfortable for 7B Q4 models at ~25-35 tok/s. Bandwidth-limited like the rest of Pascal but the 8 GB headroom matters — fits 7B with reasonable co…
- [NVIDIA GeForce GTX 1080](https://www.runlocalai.co/hardware/nvidia-gtx-1080): Pascal flagship for two years. 8 GB GDDR5X at 320 GB/s — better bandwidth than the 1070. Runs 7B Q4 at ~30-45 tok/s; 13B Q4 with offload but slow. The pre-Turing flagship that sti…
- [NVIDIA GeForce GTX 1080 Ti](https://www.runlocalai.co/hardware/nvidia-gtx-1080-ti): Pascal halo card. 11 GB GDDR5X at 484 GB/s — outperforms many newer mid-range cards on raw bandwidth. Runs 7B Q4 at ~50-65 tok/s, 13B Q4 fits comfortably at ~25-35 tok/s. The lege…
- [NVIDIA GeForce GTX 1650](https://www.runlocalai.co/hardware/nvidia-gtx-1650): Turing entry without RT/Tensor cores. 4 GB VRAM keeps it at the practical floor — 1-3B Q4 only. The 'I built a budget gaming PC' audience runs into VRAM walls almost immediately.…
- [NVIDIA GeForce GTX 1650 Super](https://www.runlocalai.co/hardware/nvidia-gtx-1650-super): Turing entry refresh with GDDR6. 4 GB VRAM is below the practical AI floor — 1-3B Q4 only. No Tensor cores. Common in pre-built office PCs from 2019-2021 that are now hitting the…
- [NVIDIA GeForce GTX 1660](https://www.runlocalai.co/hardware/nvidia-gtx-1660): Turing mid-range without RT cores. 6 GB VRAM fits 7B Q4 with short context. No Tensor cores or FP16 acceleration on consumer Turing-LITE, so inference is bandwidth-limited at ~20-…
- [NVIDIA GeForce GTX 1660 Super](https://www.runlocalai.co/hardware/nvidia-gtx-1660-super): Turing mid-range with GDDR6 — bandwidth jumps to 336 GB/s vs the base 1660. Same 6 GB VRAM ceiling but ~30-45 tok/s on 7B Q4 thanks to the bandwidth bump. Still no Tensor cores. S…
- [NVIDIA GeForce GTX 1660 Ti](https://www.runlocalai.co/hardware/nvidia-gtx-1660-ti): Turing mid-tier without RT/Tensor cores. 6 GB VRAM fits 7B Q4 with short context. Bandwidth (288 GB/s) is solid for the tier — ~30-40 tok/s on 7B Q4. Same VRAM ceiling as the 1660…
- [NVIDIA H100 NVL](https://www.runlocalai.co/hardware/nvidia-h100-nvl): Dual-card H100 with 188GB combined memory. Built for LLM serving.
- [NVIDIA H100 PCIe](https://www.runlocalai.co/hardware/nvidia-h100-pcie): PCIe Hopper. Lower power, lower bandwidth than SXM. Server-tier.
- [NVIDIA H100 SXM](https://www.runlocalai.co/hardware/nvidia-h100-sxm): Hopper SXM5 — 80GB HBM3 at 3.35 TB/s. The original GPU that trained GPT-4. Cloud-rentable.
- [NVIDIA H20 (96GB)](https://www.runlocalai.co/hardware/nvidia-h20): The China-market Hopper SKU tuned for inference: 96GB HBM3 (more than the standard H100's 80GB), 4.0 TB/s, 400W, with ~41% fewer cores than a full H100. Export-compliant and highl…
- [NVIDIA H200](https://www.runlocalai.co/hardware/nvidia-h200): Hopper refresh — 141GB HBM3e at ~4.8 TB/s. Datacenter-class; rentable on RunPod, Lambda, etc.
- [NVIDIA L4](https://www.runlocalai.co/hardware/nvidia-l4): Inference-focused Ada datacenter card. Low-power 24GB suitable for 7B-14B serving.
- [NVIDIA L40](https://www.runlocalai.co/hardware/nvidia-l40): Original Ada datacenter. Slower than L40S. 48GB GDDR6.
- [NVIDIA L40S](https://www.runlocalai.co/hardware/nvidia-l40s): Ada-gen datacenter card. 48GB GDDR6 — popular at cloud GPU rentals as a budget H100 alternative.
- [AMD Radeon 780M (Phoenix iGPU)](https://www.runlocalai.co/hardware/radeon-780m): AMD's 780M iGPU (Ryzen 7040/8040 series Phoenix). Shares system RAM via unified memory architecture; 32 GB DDR5 system gives effective 16-20 GB usable for inference. Bandwidth (89…
- [AMD Radeon 880M (Strix Point iGPU)](https://www.runlocalai.co/hardware/radeon-880m): AMD's 880M iGPU (Ryzen AI 300 series Strix Point). RDNA 3.5 with LPDDR5x-7500 unified memory — bandwidth jump from 780M (89 → 102 GB/s). ~8-15 tok/s on 7B Q4. Pairs with the dedic…
- [Razer Blade 16 (2025, RTX 5090 Mobile)](https://www.runlocalai.co/hardware/razer-blade-16-2025): Top-end Windows AI laptop with 24GB RTX 5090 Mobile.
- [NVIDIA GeForce RTX 2060](https://www.runlocalai.co/hardware/rtx-2060): First consumer card with Tensor cores at the ~$200 used tier. 6 GB VRAM is the bottleneck — 7B Q4 fits with limited context. FP16/INT8 Tensor compute makes ExLlamaV2 actually fast…
- [NVIDIA GeForce RTX 2060 Super](https://www.runlocalai.co/hardware/rtx-2060-super): Turing mid with the 8 GB upgrade — meaningful for AI. 7B Q4 fits comfortably with full context, 13B Q4 fits with offload. ~60-75 tok/s on 7B with ExLlamaV2. The '8 GB Turing' floo…
- [NVIDIA GeForce RTX 2080 Super](https://www.runlocalai.co/hardware/rtx-2080-super): Turing 'almost-flagship'. 8 GB VRAM is the ceiling — same as base 2080 — but more bandwidth (496 GB/s) and Tensor compute. Runs 7B Q4 at ~80-105 tok/s with ExLlamaV2. The 8 GB cei…
- [NVIDIA GeForce RTX 2080 Ti](https://www.runlocalai.co/hardware/rtx-2080-ti): Turing flagship. 11 GB GDDR6 at 616 GB/s — fits 13B Q4 comfortably, 7B Q4 at ~110-140 tok/s. Used $360-420 in 2026 makes it the 'enthusiast on a budget' floor; competes with used…
- [NVIDIA GeForce RTX 3050 Ti (Mobile)](https://www.runlocalai.co/hardware/rtx-3050-ti): Mobile-only Ampere with 4 GB VRAM at 192 GB/s. The 4 GB ceiling is the bottleneck — 1-3B Q4 only with no headroom for context. CUDA + Tensor cores work, but VRAM keeps the workloa…
- [NVIDIA GeForce RTX 3060 12GB](https://www.runlocalai.co/hardware/rtx-3060-12gb): The community pick for 'cheapest CUDA card with serious VRAM'. The value floor for local AI in 2026.
- [NVIDIA GeForce RTX 3060 Ti](https://www.runlocalai.co/hardware/rtx-3060-ti): Ampere mid-high with 8 GB at 448 GB/s. Comfortable for 7B Q4 (~80-100 tok/s) and 13B Q4 with light offload. The 'middle' of Ampere — better bandwidth than the 3060 12GB, less VRAM…
- [NVIDIA GeForce RTX 3070](https://www.runlocalai.co/hardware/rtx-3070): 8GB Ampere. Fits 7B Q4 only.
- [NVIDIA GeForce RTX 3080 10GB](https://www.runlocalai.co/hardware/rtx-3080-10gb): Original 10GB 3080. Tight on VRAM for AI but still capable for 7B work.
- [NVIDIA GeForce RTX 3080 12GB](https://www.runlocalai.co/hardware/rtx-3080-12gb): Mid-life 12GB refresh of the 3080. Decent 7B–14B card on the used market.
- [NVIDIA GeForce RTX 3080 16GB (Mobile)](https://www.runlocalai.co/hardware/rtx-3080-16gb-mobile): Laptop variant of Ampere. 16GB VRAM in a portable form factor was rare and remains a sleeper pick on the used market.
- [NVIDIA GeForce RTX 3080 Ti](https://www.runlocalai.co/hardware/rtx-3080-ti): Ampere flagship-minus-one. 12 GB GDDR6X at 912 GB/s — closer to the 3090 in raw bandwidth than to the 3080. Fits 13B Q4 with full context, 32B Q4 with offload. ~155-205 tok/s on 7…
- [NVIDIA GeForce RTX 3090](https://www.runlocalai.co/hardware/rtx-3090): The original 24GB CUDA value pick. Used market still strong in 2026 — many AI hobbyists run dual 3090 setups for 70B inference.
- [NVIDIA GeForce RTX 3090 Ti](https://www.runlocalai.co/hardware/rtx-3090-ti): Highest-tier Ampere consumer card. Used market gold for AI: 24GB at sub-$1200 in 2026.
- [NVIDIA GeForce RTX 4060](https://www.runlocalai.co/hardware/rtx-4060): Entry-level Ada. 8GB limits to 7B Q4.
- [NVIDIA GeForce RTX 4060 Ti 16GB](https://www.runlocalai.co/hardware/rtx-4060-ti-16gb): The poster child of 'cheap 16GB CUDA card'. Memory bandwidth is mediocre but 16GB at $400-something opens up 14B Q4.
- [NVIDIA GeForce RTX 4060 Ti 8GB](https://www.runlocalai.co/hardware/rtx-4060-ti-8gb): 8GB version — go 16GB SKU for AI work.
- [NVIDIA GeForce RTX 4070](https://www.runlocalai.co/hardware/rtx-4070): Original 4070. 12GB Ada. Now eclipsed by 4070 Super at the same price.
- [NVIDIA GeForce RTX 4070 Super](https://www.runlocalai.co/hardware/rtx-4070-super): Refreshed 4070. Strong mid-range value for 12GB-tier local AI.
- [NVIDIA GeForce RTX 4070 Ti](https://www.runlocalai.co/hardware/rtx-4070-ti): 12GB Ada — fits 7B–14B Q4 with usable context.
- [NVIDIA GeForce RTX 4070 Ti Super](https://www.runlocalai.co/hardware/rtx-4070-ti-super): 16GB upgrade of the 4070 Ti. Solid mid-high pick for local AI.
- [NVIDIA GeForce RTX 4080](https://www.runlocalai.co/hardware/rtx-4080): Original 4080. 16GB GDDR6X. Still capable for 14B–32B Q4 work.
- [NVIDIA GeForce RTX 4080 Super](https://www.runlocalai.co/hardware/rtx-4080-super): Refreshed 4080 with 16GB GDDR6X. Slightly behind 5080 but well-supported.
- [NVIDIA GeForce RTX 4090](https://www.runlocalai.co/hardware/rtx-4090): 24 GB GDDR6X at about 1 TB/s. Check 32B Q4 models against your context budget; 70B Q4 weights exceed this card’s memory and require offload or multiple GPUs.
- [NVIDIA GeForce RTX 4090 Mobile](https://www.runlocalai.co/hardware/rtx-4090-mobile): Mobile Ada flagship. 16GB VRAM in a laptop. Premium gaming and AI laptop default.
- [NVIDIA RTX 5000 Ada Generation](https://www.runlocalai.co/hardware/rtx-5000-ada): 32GB workstation Ada. Mid-tier pro card.
- [NVIDIA GeForce RTX 5050](https://www.runlocalai.co/hardware/rtx-5050): The cheapest Blackwell desktop card ($249) and the entry point to the RTX 50 series. 8GB GDDR6, 128-bit, 320 GB/s, 130W. A budget CUDA option for small LLMs and Stable Diffusion o…
- [NVIDIA GeForce RTX 5060](https://www.runlocalai.co/hardware/rtx-5060): Entry Blackwell. 8GB limits to 7B Q4 with limited context.
- [NVIDIA GeForce RTX 5060 Ti 16GB](https://www.runlocalai.co/hardware/rtx-5060-ti-16gb): The 16GB sub-$500 sweet spot. Best value for entering local AI seriously.
- [NVIDIA GeForce RTX 5060 Ti 8GB](https://www.runlocalai.co/hardware/rtx-5060-ti-8gb): 8GB Blackwell. Capable of 7B Q4 only — go 16GB SKU instead for AI work.
- [NVIDIA GeForce RTX 5070](https://www.runlocalai.co/hardware/rtx-5070): Mid-range Blackwell with 12GB. 7B-14B Q4 territory.
- [NVIDIA GeForce RTX 5070 Laptop GPU](https://www.runlocalai.co/hardware/rtx-5070-mobile): The volume mainstream RTX 50-series gaming-laptop GPU. Originally 8GB, a 12GB variant launched April 2026 to relieve VRAM pressure. GB206, 4,608 CUDA cores, 128-bit. The everyday…
- [NVIDIA GeForce RTX 5070 Ti](https://www.runlocalai.co/hardware/rtx-5070-ti): 16GB Blackwell at the upper-mid price tier. Strong 14B–32B model performance.
- [NVIDIA GeForce RTX 5080](https://www.runlocalai.co/hardware/rtx-5080): Second-tier Blackwell. 16GB GDDR7, ~960 GB/s bandwidth. Fastest 16GB consumer card on the market.
- [NVIDIA GeForce RTX 5090](https://www.runlocalai.co/hardware/rtx-5090): Blackwell flagship with 32 GB GDDR7 and about 1.79 TB/s memory bandwidth. More context headroom than a 24 GB card for 32B Q4; 70B Q4 still requires offload or more GPU memory.
- [NVIDIA GeForce RTX 5090 Mobile](https://www.runlocalai.co/hardware/rtx-5090-mobile): Mobile Blackwell flagship. 24GB GDDR7 in a laptop is the new high-water mark.
- [NVIDIA RTX 6000 Ada Generation](https://www.runlocalai.co/hardware/rtx-6000-ada): Pro Ada — 48GB ECC. Pre-Blackwell workstation default.
- [NVIDIA RTX A5000](https://www.runlocalai.co/hardware/rtx-a5000): 24GB Ampere workstation card. Tighter power envelope than RTX 3090.
- [NVIDIA RTX A6000 (Ampere)](https://www.runlocalai.co/hardware/rtx-a6000): Ampere-gen workstation card with 48GB. Common in AI labs; used market is reasonable for 48GB at this point.
- [NVIDIA RTX PRO 4000 Blackwell](https://www.runlocalai.co/hardware/rtx-pro-4000-blackwell): Single-slot 140W Blackwell workstation card with 24GB GDDR7. The low-power, compact entry to the RTX PRO Blackwell line — fits small workstations and dense multi-card builds for l…
- [NVIDIA RTX PRO 4500 Blackwell](https://www.runlocalai.co/hardware/rtx-pro-4500-blackwell): Mid-tier Blackwell workstation card: 32GB GDDR7, 200W, explicitly pitched for desktop LLM inference and generative AI. Fills the single-card 32GB local-inference slot between the…
- [NVIDIA RTX PRO 6000 Blackwell](https://www.runlocalai.co/hardware/rtx-pro-6000-blackwell): Pro Blackwell — 96GB GDDR7 ECC. The single-card answer to 70B and 100B+ local inference.
- [AMD Radeon RX 7600 XT](https://www.runlocalai.co/hardware/rx-7600-xt): Sub-$330 16GB AMD. Memory-bandwidth-limited but great VRAM-per-dollar.
- [AMD Radeon RX 7700 XT](https://www.runlocalai.co/hardware/rx-7700-xt): 12GB RDNA 3.
- [AMD Radeon RX 7800 XT](https://www.runlocalai.co/hardware/rx-7800-xt): 16GB RDNA 3 mid-range.
- [AMD Radeon RX 7900 XT](https://www.runlocalai.co/hardware/rx-7900-xt): 20GB RDNA 3. Cheaper alternative to XTX.
- [AMD Radeon RX 7900 XTX](https://www.runlocalai.co/hardware/rx-7900-xtx): AMD's 24GB challenger to the 4090. ROCm Linux now solid for llama.cpp and vLLM. Best price-per-VRAM-GB on the new market.
- [AMD Radeon RX 9070](https://www.runlocalai.co/hardware/rx-9070): 16GB RDNA 4 at sub-$600. ROCm + Vulkan supported.
- [AMD Radeon RX 9070 GRE](https://www.runlocalai.co/hardware/rx-9070-gre): The 12GB member of AMD's RDNA4 desktop line, now a global SKU ($549) after a year as a China-only 'Golden Rabbit Edition'. Navi 48, 48 CUs, 192-bit, 432 GB/s, 220W. Sits between t…
- [AMD Radeon RX 9070 XT](https://www.runlocalai.co/hardware/rx-9070-xt): RDNA 4 flagship. 16GB at $599 — best AMD value for local AI in 2026.
- [Qualcomm Snapdragon 8 Elite](https://www.runlocalai.co/hardware/snapdragon-8-elite): Late-2024 Android flagship SoC. Oryon CPU + Hexagon NPU at ~80 TOPS INT8. 8B-class models become viable on-device with adequate quantization.
- [Qualcomm Snapdragon 8 Gen 3](https://www.runlocalai.co/hardware/snapdragon-8-gen-3): Flagship Android SoC. Hexagon NPU at 45 TOPS INT8. First mainstream phone NPU to run 7B-class models on-device via Qualcomm AI Hub + ONNX Runtime Mobile.
- [Qualcomm Snapdragon X Elite](https://www.runlocalai.co/hardware/snapdragon-x-elite): Copilot+ PC reference SoC. 12-core Oryon CPU + Adreno GPU + Hexagon NPU at 45 TOPS INT8. The first ARM Windows laptop with serious NPU compute; runs Phi Silica and other on-device…
- [Qualcomm Snapdragon X Plus](https://www.runlocalai.co/hardware/snapdragon-x-plus): Lower-tier Snapdragon X. 45 TOPS NPU.
- [Qualcomm Snapdragon X2 Elite](https://www.runlocalai.co/hardware/snapdragon-x2-elite): Second-gen Snapdragon PC platform (retail H1 2026), succeeding the X Elite/X Plus. Highest laptop NPU at 80 TOPS Hexagon, up to 18 Oryon cores at 5GHz; some SKUs ship 48GB memory.…

## Tools (95)
- [Aider](https://www.runlocalai.co/tools/aider): Terminal-based AI pair programmer. Run in your project directory, describe a change, it edits files and creates meaningful git commits. Works with any LLM — local Ollama, Anthropi…
- [AnythingLLM](https://www.runlocalai.co/tools/anythingllm): Document-oriented LLM frontend with workspaces. Connects to Ollama, LM Studio, OpenAI, Anthropic, etc. Strong document RAG.
- [Aphrodite Engine](https://www.runlocalai.co/tools/aphrodite-engine): vLLM fork specialized for creative writing / role-play workloads. Adds samplers (smoothing factor, dynatemp, mirostat, DRY, XTC) that mainline vLLM doesn't ship. Same continuous-b…
- [Stable Diffusion WebUI (AUTOMATIC1111)](https://www.runlocalai.co/tools/automatic1111): The original Stable Diffusion frontend. Less actively developed in 2026 than ComfyUI but still has the cleanest UX for simple gen.
- [Axolotl](https://www.runlocalai.co/tools/axolotl): YAML-config fine-tuning framework. Reference toolkit for the open fine-tuning community (Hermes, Dolphin, etc. all use it).
- [Chroma](https://www.runlocalai.co/tools/chroma): Open-source embedding database for LLM applications. The default 'just install pip and start' vector store for prototypes, with first-party clients in Python and JS. SQLite-backed…
- [Claude Code](https://www.runlocalai.co/tools/claude-code): Anthropic's terminal-native coding agent. Tops SWE-bench Verified at 87.6% and SWE-bench Pro at 64.3% in 2026. Deep MCP integration, agentic file editing, and a $20/mo Pro tier ar…
- [Claude Desktop](https://www.runlocalai.co/tools/claude-desktop): Anthropic's official desktop app for Claude. Native MCP server support means you can plug in local file access, GitHub, and custom tools. Distinct from the Claude Code CLI.
- [Cline](https://www.runlocalai.co/tools/cline): VS Code extension agent — ~4M installs in 2026. Plan/Act mode, autonomous file edits with diff approval, terminal access. The leading open-source IDE agent.
- [ComfyUI](https://www.runlocalai.co/tools/comfyui): Node-graph image-generation UI. Standard for Stable Diffusion and Flux workflows. Endlessly customizable.
- [Continue](https://www.runlocalai.co/tools/continue): Open-source VS Code and JetBrains assistant. Configurable autocomplete + chat + agent modes. Strong with local Ollama backends.
- [CTranslate2](https://www.runlocalai.co/tools/ctranslate2): Specialized transformer inference engine. The reference runtime for Whisper (faster-whisper), NLLB translation, and other encoder-decoder models. Out-of-the-box INT8 quantization…
- [Cursor](https://www.runlocalai.co/tools/cursor): Anysphere's AI-native IDE. Forks VS Code with Cursor Tab inline completion, agentic chat, and background agents. Best 'flow' for inline completion in 2026.
- [Devin](https://www.runlocalai.co/tools/devin): Cognition Labs' fully autonomous SWE agent. Cloud-only, browser interface, longest task horizons. Premium pricing.
- [DirectML](https://www.runlocalai.co/tools/directml): Microsoft's DirectX 12 inference backend. The Windows-native path for AMD / Intel / Qualcomm GPU + NPU acceleration without ROCm or vendor-specific SDKs. Used through ONNX Runtime…
- [Droid (Factory)](https://www.runlocalai.co/tools/droid): Factory's autonomous SWE agent. Operates over GitHub PRs, Slack, Linear. Targets the long-running multi-file change workflow.
- [ExecuTorch](https://www.runlocalai.co/tools/executorch): PyTorch's official mobile / edge inference runtime. Compiles PyTorch models to a mobile-optimized format for Android (NNAPI / GPU / NPU) and iOS (Metal / CoreML). The successor to…
- [ExLlamaV2](https://www.runlocalai.co/tools/exllamav2): Hand-optimized inference for EXL2-quantized models. Fastest single-GPU runtime for the EXL2 quant format on Ada/Hopper hardware. Lower-level than llama.cpp; pairs with text-genera…
- [Exo](https://www.runlocalai.co/tools/exo): Personal AI cluster software. Auto-discovers Apple Silicon devices on a LAN and shards a model across them via pipeline + tensor parallelism on top of MLX. The 2026 unlock: Thunde…
- [Firecrawl MCP](https://www.runlocalai.co/tools/firecrawl-mcp): MCP server wrapping Firecrawl — a managed crawler that handles JavaScript rendering, anti-bot evasion, and large-site map+scrape jobs at scale. The pragmatic upgrade from mcp-serv…
- [GitHub Copilot](https://www.runlocalai.co/tools/github-copilot): GitHub's incumbent AI assistant. VS Code, JetBrains, Neovim integrations. Lost some inline-completion mindshare to Cursor and agentic mindshare to Claude Code, but still the easie…
- [Goose](https://www.runlocalai.co/tools/goose): Open-source extensible AI agent now governed by the Agentic AI Foundation (AAIF) at the Linux Foundation. Started inside Block (formerly Square). 25+ provider support including Ol…
- [GPT4All](https://www.runlocalai.co/tools/gpt4all): One of the original local-LLM apps from Nomic. Privacy-focused, runs on CPU, decent model library. Pace of development has slowed compared to Jan/Msty.
- [Graphiti (Zep)](https://www.runlocalai.co/tools/graphiti): Temporal graph memory framework. Builds a bi-temporal knowledge graph from agent conversations, tracking when each fact was learned and when it was true. Powers Zep's hosted offer…
- [Hugging Face Hub CLI](https://www.runlocalai.co/tools/huggingface-cli): The CLI for the world's model hub. hf download, hf upload, model card editing.
- [Hyperspace (P2P inference network)](https://www.runlocalai.co/tools/hyperspace): Decentralized peer-to-peer AI inference network. 2.7M+ CLI downloads, 2M+ active nodes globally as of April 2026. Three-tier model routing (local registry → DHT → gossip broadcast…
- [IPEX-LLM](https://www.runlocalai.co/tools/ipex-llm): Intel's PyTorch extension for low-bit LLM inference on Intel GPUs / CPUs / NPUs. Strongest community-supported path for running LLMs on Intel Arc A770 / B580 and on Lunar Lake NPU…
- [Jan](https://www.runlocalai.co/tools/jan): Open-source desktop ChatGPT alternative. Privacy-first, runs offline, supports Hugging Face import.
- [JetBrains AI Assistant](https://www.runlocalai.co/tools/jetbrains-ai-assistant): JetBrains' first-party AI for IntelliJ, PyCharm, WebStorm, etc. Multi-LLM backend (OpenAI, Anthropic, Gemini, local).
- [Kilo Code](https://www.runlocalai.co/tools/kilo-code): VS Code agent — 1.5M users in 2026, supports 500+ models, charges zero markup over upstream API costs. Cline lineage with Roo Code's diff approach.
- [KoboldCPP](https://www.runlocalai.co/tools/koboldcpp): Single-file llama.cpp distribution focused on roleplay and creative writing. Bundles a web UI, image gen, and the Kobold API.
- [LanceDB](https://www.runlocalai.co/tools/lancedb): Embedded vector + columnar database. Lance file format reads serverless from S3/local disk; no separate process to run. The pick for embedded apps and notebook workflows.
- [LangChain](https://www.runlocalai.co/tools/langchain): Python/JS framework for chains, agents, and RAG. Batteries-included but heavyweight; many graduate to LangGraph or DIY.
- [LangSmith](https://www.runlocalai.co/tools/langsmith): LangChain's observability + evaluation platform. Trace agent runs, run evaluators against benchmark suites, version prompts. The dominant trace+eval tool for the LangChain/LangGra…
- [Letta (memory framework)](https://www.runlocalai.co/tools/letta): Agent memory framework that models memory like an operating system. Main context = RAM, archival storage = disk; the agent itself decides when to page. Originally MemGPT, now Lett…
- [LibreChat](https://www.runlocalai.co/tools/librechat): Open-source ChatGPT clone with multi-provider support (OpenAI, Anthropic, local LLMs via OpenAI-compatible APIs). The most popular self-hosted ChatGPT-shaped frontend. Strong mult…
- [llama.cpp](https://www.runlocalai.co/tools/llama-cpp): The bedrock of local LLM inference. Most other tools wrap or embed it. Maximum control, maximum platform support, sharpest learning curve.
- [llama-cpp-python](https://www.runlocalai.co/tools/llama-cpp-python): Python bindings for llama.cpp with an OpenAI-compatible HTTP server. The fastest path from pip install to a working local-LLM endpoint. Ships pre-built wheels with optional CUDA /…
- [Llamafile](https://www.runlocalai.co/tools/llamafile): Mozilla's single-binary llama.cpp distribution. Download one file, run on any OS without dependencies.
- [LlamaIndex](https://www.runlocalai.co/tools/llamaindex): Python/JS framework focused on RAG and document indexing. Cleaner than LangChain for retrieval-heavy use cases.
- [LM Studio](https://www.runlocalai.co/tools/lm-studio): Polished desktop GUI for local LLMs. Built-in HuggingFace search, OpenAI-compatible local server, side-by-side conversations.
- [LocalAI](https://www.runlocalai.co/tools/localai): OpenAI-API-compatible drop-in for self-hosted inference, with a multi-backend twist: the same endpoint can serve LLMs (llama.cpp / vLLM under the hood), embeddings, image gen (sta…
- [Model Context Protocol (MCP)](https://www.runlocalai.co/tools/mcp-protocol): Open protocol for LLM clients to talk to external tools and data sources. The 'USB-C for AI' that became the default in 2026 — supported by Anthropic, OpenAI, and Google DeepMind,…
- [MCP Brave Search Server](https://www.runlocalai.co/tools/mcp-server-brave-search): Reference MCP server wrapping the Brave Search API. Privacy-respecting alternative to Google/Bing endpoints — Brave does not maintain a personal-history-linked index. The default…
- [MCP Fetch Server](https://www.runlocalai.co/tools/mcp-server-fetch): Reference MCP server for fetching and converting web content. Pulls a URL, runs HTML through a readability extractor, returns markdown the model can chunk and reason over. The lig…
- [MCP Filesystem Server](https://www.runlocalai.co/tools/mcp-server-filesystem): Anthropic's reference MCP server for filesystem access. Read, write, search, move, and list files inside a configured allowlist of directories. The canonical example for understan…
- [MCP Git Server](https://www.runlocalai.co/tools/mcp-server-git): Reference MCP server for local Git repository operations. Status, diff, log, blame, branch listing — read-side operations against a checked-out repo without round-tripping to GitH…
- [MCP GitHub Server](https://www.runlocalai.co/tools/mcp-server-github): GitHub's first-party MCP server. Surfaces issues, pull requests, code search, file contents, repo metadata, Actions runs, and discussions through the protocol. Now maintained by G…
- [MCP Memory Server](https://www.runlocalai.co/tools/mcp-server-memory): Reference MCP server that gives an agent a persistent knowledge graph — entities, relations, observations stored to disk and surfaced back across sessions. The simplest path to ma…
- [Playwright MCP](https://www.runlocalai.co/tools/mcp-server-playwright): Microsoft's MCP server that drives a real browser via Playwright — Chromium, Firefox, and WebKit. Ships ~22 tools that operate against the page's accessibility tree rather than pi…
- [MCP PostgreSQL Server](https://www.runlocalai.co/tools/mcp-server-postgres): Reference MCP server that exposes a Postgres database as a query surface. Read-only by default — but worth flagging that early versions had a SQL-injection class issue where the r…
- [MCP Sequential Thinking](https://www.runlocalai.co/tools/mcp-server-sequential-thinking): Reference MCP server that gives an agent a structured scratchpad for multi-step reasoning. Each call records a numbered thought with revision and branching support — the agent can…
- [Mem0 (agent memory API)](https://www.runlocalai.co/tools/mem0): Drop-in memory layer for LLM agents. Vector + graph memory variants (Mem0g) — the graph variant builds a directed labeled knowledge graph alongside the vector store, with conflict…
- [Milvus](https://www.runlocalai.co/tools/milvus): Distributed vector database designed for billion-scale workloads. Compute-storage separation, GPU-accelerated index builds, multi-tenant from the ground up. The pick when you've o…
- [MLC LLM](https://www.runlocalai.co/tools/mlc-llm): TVM-based LLM compilation framework. Compiles models for any GPU with a Vulkan / Metal / WebGPU / CUDA backend. The most-deployed cross-platform on-device LLM runtime — runs Llama…
- [MLX-LM](https://www.runlocalai.co/tools/mlx-lm): Apple's Metal-native ML framework's LLM runner. Now competitive with llama.cpp Metal on M-series silicon, with better long-context performance.
- [MLX Swift](https://www.runlocalai.co/tools/mlx-swift): Apple's Swift bindings for MLX. The native iOS / iPadOS path for on-device LLM inference. Apple-published example apps demonstrate Llama 3.2, Phi-3.5, Qwen 2.5 running on iPhone 1…
- [Msty](https://www.runlocalai.co/tools/msty): Cross-platform desktop client supporting local and cloud models in one window. Strong on knowledge-stack RAG.
- [Neo4j GraphRAG](https://www.runlocalai.co/tools/neo4j-graphrag): Neo4j's official GraphRAG toolkit — Python library + reference patterns for building retrieval-augmented generation against a knowledge graph. The mature pick for enterprises alre…
- [Ollama](https://www.runlocalai.co/tools/ollama): The default first-pull tool for local AI. One-line model installs (ollama run llama3.1), an OpenAI-compatible HTTP API, good defaults out of the box. Built on llama.cpp.
- [ONNX Runtime](https://www.runlocalai.co/tools/onnx-runtime): Microsoft's cross-platform inference runtime for ONNX models. The reference path when you need a single runtime that targets CUDA + DirectML + CoreML + OpenVINO + ROCm from one bi…
- [ONNX Runtime Mobile](https://www.runlocalai.co/tools/onnx-runtime-mobile): Microsoft's mobile/edge variant of ONNX Runtime. The reference path for Snapdragon X / Lunar Lake / Ryzen AI on Windows + Copilot+ PC NPU acceleration. Mobile builds drop ops not…
- [Open Interpreter](https://www.runlocalai.co/tools/open-interpreter): Lets LLMs execute code locally — Python, shell, AppleScript. The original 'Code Interpreter on your machine'. Useful for automation tasks.
- [OpenAI Codex](https://www.runlocalai.co/tools/openai-codex): OpenAI's 2025 coding agent (the new Codex, distinct from the deprecated 2021 model). Cloud task-runner pattern: hand it a multi-step task, it works in a sandbox and returns a PR.
- [Codex CLI](https://www.runlocalai.co/tools/openai-codex-cli): Open-source CLI client for the new Codex agent. Local CLI that orchestrates cloud Codex models against your file tree.
- [OpenClaw](https://www.runlocalai.co/tools/openclaw): Personal AI agent with a local-first gateway architecture. Connects your local LLMs (Ollama, llama.cpp) to the messaging surfaces you already use — WhatsApp, Telegram, Slack, Disc…
- [OpenCode](https://www.runlocalai.co/tools/opencode): Open-source terminal coding agent built by the SST team. TUI-first, BYO LLM, MCP-compatible. A Claude-Code-style workflow without the Anthropic lock-in.
- [OpenHands](https://www.runlocalai.co/tools/openhands): AI-driven development agent that completes engineering tasks end-to-end — branches, code, PRs. v1.6 added a Planning Mode that drafts a plan before executing. Local-LLM-friendly v…
- [Intel OpenVINO](https://www.runlocalai.co/tools/openvino): Intel's inference toolkit. The first-class path for Intel Arc GPUs, Intel NPUs (Lunar Lake / Meteor Lake), and CPU-optimized inference on x86. Ships pre-quantized model variants t…
- [Open WebUI](https://www.runlocalai.co/tools/openwebui): Self-hosted ChatGPT-style web frontend. Pairs with Ollama or any OpenAI-compatible backend. Multi-user, RAG built in, fast.
- [Petals](https://www.runlocalai.co/tools/petals): BitTorrent-style decentralized LLM inference. Splits a model into transformer-block shards distributed across volunteer hosts on the public internet — one client runs the input/ou…
- [Phoenix (Arize AI)](https://www.runlocalai.co/tools/phoenix-arize): Open-source LLM tracing + evaluation. OpenInference standard for traces; runs locally with one pip install. The OSS-first pick for teams that want LangSmith-shaped functionality w…
- [Pi (Inflection AI)](https://www.runlocalai.co/tools/pi): Inflection AI's consumer assistant — voice-first, conversational, designed for personal use rather than coding. Powered by Inflection-2.5.
- [Pinokio](https://www.runlocalai.co/tools/pinokio): Browser-style app launcher for AI tools. One-click installs of ComfyUI, oobabooga, RVC, and many other AI apps.
- [Qdrant](https://www.runlocalai.co/tools/qdrant): Vector database written in Rust. Strong filtering (payload-based pre-filter), HNSW index with quantization variants, gRPC + REST APIs. The performance pick when you cross 10M vect…
- [Qualcomm AI Hub](https://www.runlocalai.co/tools/qualcomm-ai-hub): Qualcomm's official on-device-AI compiler + model zoo for Snapdragon NPU targets. Pre-quantized model variants for Llama, Phi, Gemma, Qwen running on Hexagon NPU. The reference pa…
- [Ray Serve](https://www.runlocalai.co/tools/ray-serve): Distributed model serving on top of Ray. Lets you stitch vLLM / SGLang / custom runtimes into a multi-replica, multi-model deployment with autoscaling, traffic splitting, and pipe…
- [Redis (vector search)](https://www.runlocalai.co/tools/redis-vector): Vector search inside the same Redis you already run. HNSW + flat indices, hybrid filtering with FT.SEARCH. The pragmatic pick when you don't want to add another service to ops.
- [Replit Agent 3](https://www.runlocalai.co/tools/replit-agent-3): Replit's full-stack scaffolder agent. Goes from prompt to deployed app on Replit's hosted runtime.
- [ROCm](https://www.runlocalai.co/tools/rocm): AMD's open-source equivalent of NVIDIA CUDA. Required for any meaningful AMD GPU inference on Linux (vLLM, llama.cpp ROCm build, ExLlamaV2). Windows ROCm is improving as of 2026 b…
- [Roo Code (sunsetting May 15, 2026)](https://www.runlocalai.co/tools/roo-code): Open-source AI dev-team extension for VS Code (1.55M installs, 23.8k GitHub stars). Discontinued: all Roo Code products — Extension, Cloud, and Router — shut down on May 15, 2026…
- [SGLang](https://www.runlocalai.co/tools/sglang): Structured generation language + runtime for LLM programs. RadixAttention reuses KV cache across prompts with shared prefixes — significant throughput wins for agent workloads whe…
- [SillyTavern](https://www.runlocalai.co/tools/sillytavern): Character-driven LLM frontend originally for role-play; widely used for any persona-driven workflow. Supports OpenAI, KoboldAI, llama.cpp, Ollama, Aphrodite, oobabooga endpoints.…
- [Sourcegraph Cody](https://www.runlocalai.co/tools/sourcegraph-cody): Sourcegraph's AI assistant. Strong at large-codebase context retrieval thanks to the underlying Sourcegraph index.
- [TabbyAPI](https://www.runlocalai.co/tools/tabbyapi): OpenAI-API frontend for ExLlamaV2. Wraps the EXL2 inference engine in a clean HTTP API, adds streaming, batching, and OAI-compatible chat templates. The default front-of-house whe…
- [TensorRT-LLM](https://www.runlocalai.co/tools/tensorrt-llm): NVIDIA's first-party inference compiler. Generates optimized engines per model + GPU pair, with the lowest latency on NVIDIA hardware. The pick when you're committed to a single S…
- [Text Generation WebUI (oobabooga)](https://www.runlocalai.co/tools/text-generation-webui): The 'AUTOMATIC1111 of LLMs'. Kitchen-sink Gradio UI with multi-backend support and a big extension ecosystem.
- [Text Generation Inference (TGI)](https://www.runlocalai.co/tools/tgi): HuggingFace's production inference server. Slightly behind vLLM on raw throughput but tighter integration with the HF ecosystem.
- [TurboVec](https://www.runlocalai.co/tools/turbovec): TurboVec is an open-source, local-first vector index (Rust core + Python bindings) by Ryan Codrai, MIT-licensed, built on Google Research's TurboQuant quantizer (presented at ICLR…
- [Unsloth](https://www.runlocalai.co/tools/unsloth): 2x faster QLoRA fine-tuning with hand-tuned Triton kernels. Free OSS for single-GPU; commercial Pro for multi-GPU.
- [vLLM](https://www.runlocalai.co/tools/vllm): High-throughput inference engine with PagedAttention, continuous batching, and tensor + pipeline parallelism. The reference deployment runtime when you've outgrown llama.cpp / Oll…
- [Weaviate](https://www.runlocalai.co/tools/weaviate): Vector database with built-in modules for embedding, generative search, and reranking. Schema-first design appeals to teams used to traditional databases. Generative-search module…
- [Windsurf (Codeium)](https://www.runlocalai.co/tools/windsurf): Codeium's AI-native IDE (formerly known as Codeium). Cascade agent, supercomplete, and a generous free tier.
- [Zed (with AI)](https://www.runlocalai.co/tools/zed-ai): High-performance native editor from the Atom team, with built-in AI panel and inline assistant. BYO API key for any provider.
- [Zep (memory platform)](https://www.runlocalai.co/tools/zep): Long-term memory platform for AI agents. Sits above Graphiti as the application layer — sessions, facts, summaries, vector + graph hybrid retrieval. The 'memory backend you don't…

## Buyer guides (80)
- [Best Gpu For Local Ai](https://www.runlocalai.co/guides/best-gpu-for-local-ai)
- [Best Gpu For Local Ai 2026](https://www.runlocalai.co/guides/best-gpu-for-local-ai-2026)
- [Choosing A Gpu For Local Ai 2026](https://www.runlocalai.co/guides/choosing-a-gpu-for-local-ai-2026)
- [Best Hardware For Running Local Ai Models](https://www.runlocalai.co/guides/best-hardware-for-running-local-ai-models)
- [Best Mobile Ai Runtimes](https://www.runlocalai.co/guides/best-mobile-ai-runtimes)
- [Best Free Local Ai Tools](https://www.runlocalai.co/guides/best-free-local-ai-tools)
- [Best Free Local Ai Tools 2026](https://www.runlocalai.co/guides/best-free-local-ai-tools-2026)
- [Best Used Gpu For Local Ai](https://www.runlocalai.co/guides/best-used-gpu-for-local-ai)
- [Best Budget Gpu For Local Ai](https://www.runlocalai.co/guides/best-budget-gpu-for-local-ai)
- [16gb Vs 24gb Vram For Local Ai](https://www.runlocalai.co/guides/16gb-vs-24gb-vram-for-local-ai)
- [Best Laptop For Local Ai](https://www.runlocalai.co/guides/best-laptop-for-local-ai)
- [Best Mac For Local Ai](https://www.runlocalai.co/guides/best-mac-for-local-ai)
- [Best Gpu For Ollama](https://www.runlocalai.co/guides/best-gpu-for-ollama)
- [Best Gpu For Stable Diffusion Local](https://www.runlocalai.co/guides/best-gpu-for-stable-diffusion-local)
- [Cuda Vs Rocm](https://www.runlocalai.co/guides/cuda-vs-rocm)
- [Best Ai Pc Build Under 1000](https://www.runlocalai.co/guides/best-ai-pc-build-under-1000)
- [Best Ai Pc Build Under 2000](https://www.runlocalai.co/guides/best-ai-pc-build-under-2000)
- [Best Gpu For Qwen](https://www.runlocalai.co/guides/best-gpu-for-qwen)
- [Best Gpu For Deepseek](https://www.runlocalai.co/guides/best-gpu-for-deepseek)
- [Best Gpu For Llama](https://www.runlocalai.co/guides/best-gpu-for-llama)
- [Best Gpu For Flux](https://www.runlocalai.co/guides/best-gpu-for-flux)
- [Best Gpu For Whisper](https://www.runlocalai.co/guides/best-gpu-for-whisper)
- [Best Gpu For Rag](https://www.runlocalai.co/guides/best-gpu-for-rag)
- [Best Ai Pc For Students](https://www.runlocalai.co/guides/best-ai-pc-for-students)
- [Best Ai Pc For Developers](https://www.runlocalai.co/guides/best-ai-pc-for-developers)
- [Best Ai Pc For Small Business](https://www.runlocalai.co/guides/best-ai-pc-for-small-business)
- [Best Budget Mac For Local Ai](https://www.runlocalai.co/guides/best-budget-mac-for-local-ai)
- [Best Mini Pc For Local Ai](https://www.runlocalai.co/guides/best-mini-pc-for-local-ai)
- [Best Igpu For Local Ai](https://www.runlocalai.co/guides/best-igpu-for-local-ai)
- [Best Egpu Setup For Local Ai](https://www.runlocalai.co/guides/best-egpu-setup-for-local-ai)
- [Best Gpu For Comfyui](https://www.runlocalai.co/guides/best-gpu-for-comfyui)
- [Best Gpu For Koboldcpp](https://www.runlocalai.co/guides/best-gpu-for-koboldcpp)
- [Best Gpu For Ai Agents](https://www.runlocalai.co/guides/best-gpu-for-ai-agents)
- [Best Gpu For Voice Cloning](https://www.runlocalai.co/guides/best-gpu-for-voice-cloning)
- [Best Upgrade From Rtx 3060](https://www.runlocalai.co/guides/best-upgrade-from-rtx-3060)
- [Best Gpu For Local Video Generation](https://www.runlocalai.co/guides/best-gpu-for-local-video-generation)
- [Best Gpu For Local Ocr](https://www.runlocalai.co/guides/best-gpu-for-local-ocr)
- [Best Local Ai Setup For Beginners](https://www.runlocalai.co/guides/best-local-ai-setup-for-beginners)
- [Local Ai For Youtube Editing](https://www.runlocalai.co/guides/local-ai-for-youtube-editing)
- [Local Ai For Lawyers](https://www.runlocalai.co/guides/local-ai-for-lawyers)
- [Local Ai For Teachers](https://www.runlocalai.co/guides/local-ai-for-teachers)
- [Local Ai For Research](https://www.runlocalai.co/guides/local-ai-for-research)
- [Local Ai For Architects](https://www.runlocalai.co/guides/local-ai-for-architects)
- [Local Ai For Podcasters](https://www.runlocalai.co/guides/local-ai-for-podcasters)
- [Running Local Ai On Multiple Gpus 2026](https://www.runlocalai.co/guides/running-local-ai-on-multiple-gpus-2026)
- [Can I Run Ai Locally On My Computer](https://www.runlocalai.co/guides/can-i-run-ai-locally-on-my-computer)
- [Free Ai Tools That Run On Your Computer](https://www.runlocalai.co/guides/free-ai-tools-that-run-on-your-computer)
- [Local Ai Vs Chatgpt Plus](https://www.runlocalai.co/guides/local-ai-vs-chatgpt-plus)
- [Common Local Ai Setup Mistakes](https://www.runlocalai.co/guides/common-local-ai-setup-mistakes)
- [Common Local Ai Mistakes](https://www.runlocalai.co/guides/common-local-ai-mistakes)
- [How Much Does Local Ai Cost](https://www.runlocalai.co/guides/how-much-does-local-ai-cost)
- [How To Use Ai In Job Applications Ethically](https://www.runlocalai.co/guides/how-to-use-ai-in-job-applications-ethically)
- [Why Run Ai Locally Instead Of Chatgpt](https://www.runlocalai.co/guides/why-run-ai-locally-instead-of-chatgpt)
- [Local Ai Vs Chatgpt Plus For Job Hunting](https://www.runlocalai.co/guides/local-ai-vs-chatgpt-plus-for-job-hunting)
- [Does Running Ai Locally Save Money](https://www.runlocalai.co/guides/does-running-ai-locally-save-money)
- [How Long Does Local Ai Take To Set Up](https://www.runlocalai.co/guides/how-long-does-local-ai-take-to-set-up)
- [Ai Tools That Work Offline](https://www.runlocalai.co/guides/ai-tools-that-work-offline)
- [Local Ai Tools For Resume Optimization](https://www.runlocalai.co/guides/local-ai-tools-for-resume-optimization)
- [How To Troubleshoot Local Ai Job Tools](https://www.runlocalai.co/guides/how-to-troubleshoot-local-ai-job-tools)
- [Local Ai For Students](https://www.runlocalai.co/guides/local-ai-for-students)
- [Local Ai For Developers](https://www.runlocalai.co/guides/local-ai-for-developers)
- [Local Ai Hardware Under 1000](https://www.runlocalai.co/guides/local-ai-hardware-under-1000)
- [Local Ai For Privacy](https://www.runlocalai.co/guides/local-ai-for-privacy)
- [Local Ai For Freelancers](https://www.runlocalai.co/guides/local-ai-for-freelancers)
- [Local Ai For Document Search](https://www.runlocalai.co/guides/local-ai-for-document-search)
- [Local Ai For Small Business](https://www.runlocalai.co/guides/local-ai-for-small-business)
- [Local Ai For Coding Agents](https://www.runlocalai.co/guides/local-ai-for-coding-agents)
- [Methodology](https://www.runlocalai.co/guides/methodology)
- [Can Phones Run Local Llms](https://www.runlocalai.co/guides/can-phones-run-local-llms)
- [Dual 3090 Vs Single 5090](https://www.runlocalai.co/guides/dual-3090-vs-single-5090)
- [How To Benchmark Local Ai](https://www.runlocalai.co/guides/how-to-benchmark-local-ai)
- [Local Ai Benchmarking Mistakes](https://www.runlocalai.co/guides/local-ai-benchmarking-mistakes)
- [Run Local Ai On Android](https://www.runlocalai.co/guides/run-local-ai-on-android)
- [Run Local Ai On Iphone](https://www.runlocalai.co/guides/run-local-ai-on-iphone)
- [Macos 26 5 For Local Ai](https://www.runlocalai.co/guides/macos-26-5-for-local-ai)
- [Local Ai Clusters 2026](https://www.runlocalai.co/guides/local-ai-clusters-2026)
- [Openclaw Personal Ai Agent 2026](https://www.runlocalai.co/guides/openclaw-personal-ai-agent-2026)
- [Codex Cli With Local Models](https://www.runlocalai.co/guides/codex-cli-with-local-models)
- [Claude Code With Local Models](https://www.runlocalai.co/guides/claude-code-with-local-models)
- [Gemini Cli With Local Models](https://www.runlocalai.co/guides/gemini-cli-with-local-models)

## How-to guides (352)
- [How to Add File System Operations as Agent Tools](https://www.runlocalai.co/learn/how-to/add-file-system-operations-agent-tools)
- [How to Add Human-in-the-Loop to LangGraph Workflows](https://www.runlocalai.co/learn/how-to/add-human-in-the-loop-langgraph)
- [How to Add Query Expansion to Improve Recall](https://www.runlocalai.co/learn/how-to/add-query-expansion-improve-recall)
- [How to Add Rate Limiting to Agent Tool Calls](https://www.runlocalai.co/learn/how-to/add-rate-limiting-agent-tool-calls)
- [How to Add Reranking to Your RAG Pipeline](https://www.runlocalai.co/learn/how-to/add-reranking-rag-pipeline)
- [How to Add Streaming to LangChain Chains](https://www.runlocalai.co/learn/how-to/add-streaming-langchain-chains)
- [How to adjust context length when running on limited hardware](https://www.runlocalai.co/learn/how-to/adjust-context-length-limited-hardware)
- [How to allocate specific GPU memory limits per model](https://www.runlocalai.co/learn/how-to/allocate-specific-gpu-memory-per-model)
- [How to allocate token budgets across system prompts, context window, and responses](https://www.runlocalai.co/learn/how-to/allocate-token-budgets-system-prompt-context)
- [How to Apply Metadata Filters to Reduce Search Space](https://www.runlocalai.co/learn/how-to/apply-metadata-filters-reduce-search-space)
- [How to implement async prompt logging to S3 without blocking inference latency](https://www.runlocalai.co/learn/how-to/async-prompt-logging-s3)
- [How to Batch Ingest Documents into Vector Database](https://www.runlocalai.co/learn/how-to/batch-ingest-documents-vector-database)
- [How to benchmark DeepSeek against dense models of similar size](https://www.runlocalai.co/learn/how-to/benchmark-deepseek-vs-dense-models)
- [How to benchmark first-token latency for interactive applications](https://www.runlocalai.co/learn/how-to/benchmark-first-token-latency)
- [How to benchmark model response time using the Ollama API](https://www.runlocalai.co/learn/how-to/benchmark-model-response-time-api)
- [How to benchmark models with varying context lengths](https://www.runlocalai.co/learn/how-to/benchmark-models-varying-context-lengths)
- [How to benchmark reasoning capabilities between DeepSeek-R1 and other models](https://www.runlocalai.co/learn/how-to/benchmark-reasoning-deepseek-vs-others)
- [How to benchmark token generation speed in tokens per second](https://www.runlocalai.co/learn/how-to/benchmark-token-generation-speed)
- [How to build an AI content generation pipeline](https://www.runlocalai.co/learn/how-to/build-ai-content-generation-pipeline)
- [How to Build an AI-Powered Email Automation System](https://www.runlocalai.co/learn/how-to/build-ai-email-automation-system)
- [How to Build a Basic RAG Pipeline with LangChain](https://www.runlocalai.co/learn/how-to/build-basic-rag-pipeline-langchain)
- [How to Build BM25 and Vector Hybrid Retrieval](https://www.runlocalai.co/learn/how-to/build-bm25-vector-hybrid-retrieval)
- [How to build a code generation agent with local models](https://www.runlocalai.co/learn/how-to/build-code-generation-agent-local-models)
- [How to Build Context-Aware RAG with Follow-Up Questions](https://www.runlocalai.co/learn/how-to/build-context-aware-rag-follow-up)
- [How to Build Conversational RAG with Memory](https://www.runlocalai.co/learn/how-to/build-conversational-rag-memory)
- [How to Build Core AI Agent Architecture](https://www.runlocalai.co/learn/how-to/build-core-ai-agent-architecture)
- [How to build a cost tracking dashboard for AI usage](https://www.runlocalai.co/learn/how-to/build-cost-tracking-dashboard-ai)
- [How to build a custom AI coding assistant](https://www.runlocalai.co/learn/how-to/build-custom-ai-coding-assistant)
- [How to build custom Docker image for AI models](https://www.runlocalai.co/learn/how-to/build-custom-docker-image-ai)
- [How to Build Custom LLM Chain with Prompt Templates](https://www.runlocalai.co/learn/how-to/build-custom-llm-chain-prompt-templates)
- [How to build a custom prompt template library](https://www.runlocalai.co/learn/how-to/build-custom-prompt-template-library)
- [How to Build Custom Tools for Agents](https://www.runlocalai.co/learn/how-to/build-custom-tools-agents)
- [How to build a decision tree prompt chain that routes user queries based on detected intent](https://www.runlocalai.co/learn/how-to/build-decision-tree-prompt-chain)
- [How to build a document analysis agent pipeline](https://www.runlocalai.co/learn/how-to/build-document-analysis-agent-pipeline)
- [How to Build Error Handling in Agent Pipelines](https://www.runlocalai.co/learn/how-to/build-error-handling-agent-pipelines)
- [How to build a LangGraph agent from scratch](https://www.runlocalai.co/learn/how-to/build-langgraph-agent-scratch)
- [How to build a local AI product with Nigerian naira pricing](https://www.runlocalai.co/learn/how-to/build-local-ai-product-naira-pricing)
- [How to Build Multi-Agent Orchestration System](https://www.runlocalai.co/learn/how-to/build-multi-agent-orchestration)
- [How to build a multi-agent supervisor workflow](https://www.runlocalai.co/learn/how-to/build-multi-agent-supervisor-workflow)
- [How to Build Multi-Modal RAG for Images and Text](https://www.runlocalai.co/learn/how-to/build-multi-modal-rag-images-text)
- [How to build a multi-tenant AI serving infrastructure](https://www.runlocalai.co/learn/how-to/build-multi-tenant-ai-serving)
- [How to Build Query Expansion with Sub-Queries](https://www.runlocalai.co/learn/how-to/build-query-expansion-sub-queries)
- [How to build a RAG evaluation pipeline](https://www.runlocalai.co/learn/how-to/build-rag-evaluation-pipeline)
- [How to Build a Real-Time AI Monitoring Dashboard](https://www.runlocalai.co/learn/how-to/build-real-time-ai-monitoring-dashboard)
- [How to build a real-time data pipeline using Apache Kafka or Redis Streams with AI-enriched events](https://www.runlocalai.co/learn/how-to/build-real-time-data-pipeline-kafka-ai)
- [How to build a research agent that browses the web](https://www.runlocalai.co/learn/how-to/build-research-agent-browses-web)
- [How to Build RetrievalQA Chain with Sources](https://www.runlocalai.co/learn/how-to/build-retrievalqa-chain-sources)
- [How to build a scheduled web scraping job that feeds extracted data into a database using AI parsing](https://www.runlocalai.co/learn/how-to/build-scheduled-web-scraping-job)
- [How to build a structured prompt/response logging pipeline with Fluentd](https://www.runlocalai.co/learn/how-to/build-structured-prompt-logging-fluentd)
- [How to build a type-safe API client using an AI assistant that reads your OpenAPI spec](https://www.runlocalai.co/learn/how-to/build-type-safe-api-client-ai-openapi)
- [How to Build Web Search with Citation Support](https://www.runlocalai.co/learn/how-to/build-web-search-citation-support)
- [How to set up centralized logging for distributed AI agents using the ELK stack](https://www.runlocalai.co/learn/how-to/centralized-logging-elk-ai-agents)
- [How to chain prompts together to break complex tasks into sequential AI reasoning steps](https://www.runlocalai.co/learn/how-to/chain-prompts-complex-tasks-sequential)
- [How to Choose and Configure FAISS Index Types (IVF, HNSW)](https://www.runlocalai.co/learn/how-to/choose-configure-faiss-index-types)
- [How to choose the right quantization level based on your hardware](https://www.runlocalai.co/learn/how-to/choose-quantization-level-hardware)
- [How to Use ChromaDB with LangChain for Vector Storage](https://www.runlocalai.co/learn/how-to/chromadb-langchain-vector-storage)
- [How to compare embedding model performance for your use case](https://www.runlocalai.co/learn/how-to/compare-embedding-model-performance)
- [How to compare model performance across different quantization levels](https://www.runlocalai.co/learn/how-to/compare-model-performance-quantization-levels)
- [How to compare file sizes between different quantization formats](https://www.runlocalai.co/learn/how-to/compare-quantization-file-sizes)
- [How to compare two models side-by-side with identical prompts](https://www.runlocalai.co/learn/how-to/compare-two-models-side-by-side)
- [How to compare vision model outputs across different model sizes](https://www.runlocalai.co/learn/how-to/compare-vision-model-outputs-sizes)
- [How to compile llama.cpp from source](https://www.runlocalai.co/learn/how-to/compile-llama-cpp-source)
- [How to Compose Multiple Chains with Pipe Operator](https://www.runlocalai.co/learn/how-to/compose-multiple-chains-pipe-operator)
- [How to configure AI debugging breakpoints using VS Code AI-assisted debugging extension](https://www.runlocalai.co/learn/how-to/configure-ai-debugging-breakpoints-vscode)
- [How to configure batch size limits to prevent memory overflow](https://www.runlocalai.co/learn/how-to/configure-batch-size-prevent-memory-overflow)
- [How to configure a CI/CD pipeline in GitHub Actions to run AI-generated tests automatically](https://www.runlocalai.co/learn/how-to/configure-ci-cd-github-actions-ai-tests)
- [How to configure Claude Code's forbidden tool restrictions for safe usage](https://www.runlocalai.co/learn/how-to/configure-claude-code-forbidden-tools)
- [How to configure context window size for long documents](https://www.runlocalai.co/learn/how-to/configure-context-window-long-documents)
- [How to configure Continue.dev with multiple AI providers and switch between them](https://www.runlocalai.co/learn/how-to/configure-continue-dev-multiple-providers)
- [How to configure Continue.dev with Ollama](https://www.runlocalai.co/learn/how-to/configure-continue-dev-ollama)
- [How to configure DeepSeek models for reduced memory usage](https://www.runlocalai.co/learn/how-to/configure-deepseek-reduced-memory)
- [How to configure GitHub Copilot inline suggestions and keyboard shortcuts](https://www.runlocalai.co/learn/how-to/configure-github-copilot-suggestions-shortcuts)
- [How to configure GPU access in Docker Compose for AI inference](https://www.runlocalai.co/learn/how-to/configure-gpu-access-docker-compose-ai)
- [How to configure LM Studio server settings](https://www.runlocalai.co/learn/how-to/configure-lm-studio-server-settings)
- [How to configure Ollama for concurrent multi-user access](https://www.runlocalai.co/learn/how-to/configure-ollama-concurrent-multi-user)
- [How to configure Ollama port and networking](https://www.runlocalai.co/learn/how-to/configure-ollama-port-networking)
- [How to configure the Ollama serve port for network access](https://www.runlocalai.co/learn/how-to/configure-ollama-serve-port)
- [How to configure Open WebUI with Ollama backend](https://www.runlocalai.co/learn/how-to/configure-open-webui-ollama)
- [How to configure partial GPU offloading for large models](https://www.runlocalai.co/learn/how-to/configure-partial-gpu-offloading)
- [How to configure PyTorch with GPU support](https://www.runlocalai.co/learn/how-to/configure-pytorch-gpu)
- [How to configure repeat penalty to reduce looping responses](https://www.runlocalai.co/learn/how-to/configure-repeat-penalty-reduce-looping)
- [How to configure vLLM GPU memory allocation](https://www.runlocalai.co/learn/how-to/configure-vllm-gpu-memory)
- [How to connect to LM Studio from Continue.dev](https://www.runlocalai.co/learn/how-to/connect-continue-lm-studio)
- [How to Connect MCP Client to Remote MCP Server](https://www.runlocalai.co/learn/how-to/connect-mcp-client-remote-server)
- [How to use Continue.dev with custom model endpoints](https://www.runlocalai.co/learn/how-to/continue-dev-custom-model-endpoints)
- [How to use AI to convert legacy comments into idiomatic framework documentation](https://www.runlocalai.co/learn/how-to/convert-legacy-comments-framework-docs-ai)
- [How to count tokens in OpenAI API requests using the tiktoken library in Python](https://www.runlocalai.co/learn/how-to/count-tokens-openai-tiktoken)
- [How to Create Agent Decision-Making Logic](https://www.runlocalai.co/learn/how-to/create-agent-decision-making-logic)
- [How to Create Basic LangChain Chains with LCEL](https://www.runlocalai.co/learn/how-to/create-basic-langchain-chains-lcel)
- [How to Create Conditional Edges in LangGraph](https://www.runlocalai.co/learn/how-to/create-conditional-edges-langgraph)
- [How to Create Context-Aware Chunks with Parent Document](https://www.runlocalai.co/learn/how-to/create-context-aware-chunks-parent)
- [How to Create ConversationalRetrievalChain with Memory](https://www.runlocalai.co/learn/how-to/create-conversational-retrieval-chain-memory)
- [How to create custom MCP servers for file access](https://www.runlocalai.co/learn/how-to/create-custom-mcp-servers-file-access)
- [How to Create Custom MCP Tools for Your Application](https://www.runlocalai.co/learn/how-to/create-custom-mcp-tools)
- [How to create a custom Modelfile for Ollama](https://www.runlocalai.co/learn/how-to/create-custom-modelfile-ollama)
- [How to create integration test suites for REST API endpoints using AI-assisted tools](https://www.runlocalai.co/learn/how-to/create-integration-test-suites-rest-api)
- [How to Create and Manage ChromaDB Collections](https://www.runlocalai.co/learn/how-to/create-manage-chromadb-collections)
- [How to create a Modelfile to customize model parameters](https://www.runlocalai.co/learn/how-to/create-modelfile-customize-parameters)
- [How to create a multi-role system prompt with distinct personas for different coding tasks](https://www.runlocalai.co/learn/how-to/create-multi-role-system-prompt-personas)
- [How to create SLO burn rate alerts for AI agent availability](https://www.runlocalai.co/learn/how-to/create-slo-burn-rate-alerts-ai)
- [How to create a systematic model comparison matrix](https://www.runlocalai.co/learn/how-to/create-systematic-model-comparison-matrix)
- [How to create a task completion workflow in Manus AI for building a React component](https://www.runlocalai.co/learn/how-to/create-task-completion-workflow-manus-react)
- [How to customize Continue.dev prompts](https://www.runlocalai.co/learn/how-to/customize-continue-dev-prompts)
- [How to Debug Agent Reasoning and Tool Selection](https://www.runlocalai.co/learn/how-to/debug-agent-reasoning-tool-selection)
- [How to debug AI agent loops and infinite reasoning](https://www.runlocalai.co/learn/how-to/debug-ai-agent-loops-infinite-reasoning)
- [How to Debug LangChain Chain Execution](https://www.runlocalai.co/learn/how-to/debug-langchain-chain-execution)
- [How to debug memory leaks in a Node.js application using AI-powered profiling analysis](https://www.runlocalai.co/learn/how-to/debug-memory-leaks-nodejs-ai-profiling)
- [How to Define JSON Schema for Tool Calling](https://www.runlocalai.co/learn/how-to/define-json-schema-tool-calling)
- [How to Define State Schema in LangGraph](https://www.runlocalai.co/learn/how-to/define-state-schema-langgraph)
- [How to delegate specific file tasks to an AI pair programmer while you focus on architecture](https://www.runlocalai.co/learn/how-to/delegate-file-tasks-ai-pair-programmer)
- [How to delete unused models to free up disk space](https://www.runlocalai.co/learn/how-to/delete-unused-models-free-space)
- [How to deploy AI with Kubernetes and GPU nodes](https://www.runlocalai.co/learn/how-to/deploy-ai-kubernetes-gpu-nodes)
- [How to Deploy ChromaDB in Client-Server Mode](https://www.runlocalai.co/learn/how-to/deploy-chromadb-client-server)
- [How to deploy a production-grade PD like Hyperspace](https://www.runlocalai.co/learn/how-to/deploy-production-pd-hyperspace)
- [How to deploy vLLM on Kubernetes with GPU node selection](https://www.runlocalai.co/learn/how-to/deploy-vllm-kubernetes-gpu-nodes)
- [How to design a batch data pipeline that extracts from APIs, transforms with AI, and loads into a data warehouse](https://www.runlocalai.co/learn/how-to/design-batch-data-pipeline-etl-ai)
- [How to design effective system prompts that guide an AI assistant behavior and constraints](https://www.runlocalai.co/learn/how-to/design-effective-system-prompts)
- [How to Design Specialized Agent Roles](https://www.runlocalai.co/learn/how-to/design-specialized-agent-roles)
- [How to implement distributed tracing for multi-agent workflows with trace context propagation](https://www.runlocalai.co/learn/how-to/distributed-tracing-multi-agent-workflows)
- [How to create a Docker Compose setup for AI stack](https://www.runlocalai.co/learn/how-to/docker-compose-ai-stack)
- [How to create a Docker Compose stack with vLLM, Redis, and Prometheus](https://www.runlocalai.co/learn/how-to/docker-compose-vllm-redis-prometheus)
- [How to download models in LM Studio](https://www.runlocalai.co/learn/how-to/download-models-lm-studio)
- [How to download and run a model with Ollama](https://www.runlocalai.co/learn/how-to/download-run-model-ollama)
- [How to enable authentication in Open WebUI](https://www.runlocalai.co/learn/how-to/enable-authentication-open-webui)
- [How to Enable ChromaDB Persistence for Production](https://www.runlocalai.co/learn/how-to/enable-chromadb-persistence-production)
- [How to enable full GPU acceleration for maximum performance](https://www.runlocalai.co/learn/how-to/enable-full-gpu-acceleration)
- [How to Enable Function Calling in Local Models (Ollama)](https://www.runlocalai.co/learn/how-to/enable-function-calling-local-ollama)
- [How to enable prompt caching to speed up repeated queries](https://www.runlocalai.co/learn/how-to/enable-prompt-caching)
- [How to enable and configure speculative decoding for faster generation](https://www.runlocalai.co/learn/how-to/enable-speculative-decoding)
- [How to enable streaming responses for real-time output](https://www.runlocalai.co/learn/how-to/enable-streaming-responses)
- [How to enable tensor parallelism in vLLM](https://www.runlocalai.co/learn/how-to/enable-tensor-parallelism-vllm)
- [How to estimate Claude API token costs using the Anthropic token counting tool](https://www.runlocalai.co/learn/how-to/estimate-claude-token-costs)
- [How to evaluate model response quality using predefined test cases](https://www.runlocalai.co/learn/how-to/evaluate-model-quality-test-cases)
- [How to Evaluate RAG Pipeline Performance](https://www.runlocalai.co/learn/how-to/evaluate-rag-pipeline-performance)
- [How to Evaluate Reranking Quality with NDCG](https://www.runlocalai.co/learn/how-to/evaluate-reranking-quality-ndcg)
- [How to Extract Metadata from Documents for Filtering](https://www.runlocalai.co/learn/how-to/extract-metadata-documents-filtering)
- [How to Extract Tables from PDFs for Structured Data](https://www.runlocalai.co/learn/how-to/extract-tables-pdfs-structured-data)
- [How to Extract Text from PDFs Using PyMuPDF](https://www.runlocalai.co/learn/how-to/extract-text-pdfs-pymupdf)
- [How to fine-tune embedding batch sizes for your hardware](https://www.runlocalai.co/learn/how-to/fine-tune-embedding-batch-sizes)
- [How to Fine-Tune Reranking Models for Your Domain](https://www.runlocalai.co/learn/how-to/fine-tune-reranking-models-domain)
- [How to format image prompts correctly for LLaVA models](https://www.runlocalai.co/learn/how-to/format-image-prompts-llava)
- [How to use AI to generate JSDoc and TypeDoc comments for a JavaScript or TypeScript codebase](https://www.runlocalai.co/learn/how-to/generate-jsdoc-typedoc-comments-ai)
- [How to generate README documentation for a repository using an AI tool trained on Markdown](https://www.runlocalai.co/learn/how-to/generate-readme-documentation-ai)
- [How to generate unit tests for a Python function using Claude Code](https://www.runlocalai.co/learn/how-to/generate-unit-tests-python-claude-code)
- [How to implement GPU-based autoscaling with custom metrics](https://www.runlocalai.co/learn/how-to/gpu-autoscaling-custom-metrics)
- [How to create Grafana dashboards for AI agent queue depth and wait times](https://www.runlocalai.co/learn/how-to/grafana-dashboard-ai-agent-queue)
- [How to create Grafana panels for vLLM throughput monitoring](https://www.runlocalai.co/learn/how-to/grafana-panels-vllm-throughput)
- [How to handle API rate limiting and retry logic in AI-integrated API calls](https://www.runlocalai.co/learn/how-to/handle-api-rate-limiting-retry-ai)
- [How to Handle Function Call Errors and Retries](https://www.runlocalai.co/learn/how-to/handle-function-call-errors-retries)
- [How to handle high-resolution images with LLaVA](https://www.runlocalai.co/learn/how-to/handle-high-resolution-images-llava)
- [How to handle streaming response chunks in your application](https://www.runlocalai.co/learn/how-to/handle-streaming-response-chunks)
- [How to implement healthchecks and restart policies for AI containers](https://www.runlocalai.co/learn/how-to/healthchecks-restart-policies-ai-containers)
- [How to set up horizontal pod autoscaling for AI inference services](https://www.runlocalai.co/learn/how-to/horizontal-pod-autoscaling-ai-inference)
- [How to implement A/B testing for model responses](https://www.runlocalai.co/learn/how-to/implement-ab-testing-model-responses)
- [How to Implement Agent Memory (Short and Long Term)](https://www.runlocalai.co/learn/how-to/implement-agent-memory-short-long-term)
- [How to implement agent planning and task decomposition](https://www.runlocalai.co/learn/how-to/implement-agent-planning-task-decomposition)
- [How to Implement Agent Reflection and Self-Correction](https://www.runlocalai.co/learn/how-to/implement-agent-reflection-self-correction)
- [How to Implement Agent-to-Agent Communication](https://www.runlocalai.co/learn/how-to/implement-agent-to-agent-communication)
- [How to Implement AI Agent Logging and Audit Trails](https://www.runlocalai.co/learn/how-to/implement-ai-agent-logging-audit)
- [How to implement AI-powered data extraction from PDFs](https://www.runlocalai.co/learn/how-to/implement-ai-data-extraction-pdfs)
- [How to Implement Cascade Reranking for Efficiency](https://www.runlocalai.co/learn/how-to/implement-cascade-reranking-efficiency)
- [How to Implement Cohere Reranking API](https://www.runlocalai.co/learn/how-to/implement-cohere-reranking-api)
- [How to Implement Dynamic Chunk Sizing Based on Content](https://www.runlocalai.co/learn/how-to/implement-dynamic-chunk-sizing)
- [How to implement few-shot example selection dynamically](https://www.runlocalai.co/learn/how-to/implement-few-shot-example-selection)
- [How to implement guardrails for AI agents](https://www.runlocalai.co/learn/how-to/implement-guardrails-ai-agents)
- [How to implement human-in-the-loop for AI agents](https://www.runlocalai.co/learn/how-to/implement-human-in-the-loop-ai-agents)
- [How to Implement Hybrid Chunking (Semantic + Fixed Size)](https://www.runlocalai.co/learn/how-to/implement-hybrid-chunking-semantic-fixed)
- [How to Implement Hybrid Search (Keyword + Semantic)](https://www.runlocalai.co/learn/how-to/implement-hybrid-search-keyword-semantic)
- [How to Implement Hybrid Search RAG (BM25 + Vector)](https://www.runlocalai.co/learn/how-to/implement-hybrid-search-rag-bm25-vector)
- [How to Implement Logging for Agent Debugging](https://www.runlocalai.co/learn/how-to/implement-logging-agent-debugging)
- [How to Implement Memory in LangGraph State](https://www.runlocalai.co/learn/how-to/implement-memory-langgraph-state)
- [How to Implement Metadata Filtering in ChromaDB](https://www.runlocalai.co/learn/how-to/implement-metadata-filtering-chromadb)
- [How to implement parallel agent execution](https://www.runlocalai.co/learn/how-to/implement-parallel-agent-execution)
- [How to implement rate limiting for AI APIs](https://www.runlocalai.co/learn/how-to/implement-rate-limiting-ai-apis)
- [How to Implement Secure File Operations for Agents](https://www.runlocalai.co/learn/how-to/implement-secure-file-operations-agents)
- [How to Implement Self-Querying Retrieval in RAG](https://www.runlocalai.co/learn/how-to/implement-self-querying-retrieval)
- [How to Implement Semantic Chunking with LangChain](https://www.runlocalai.co/learn/how-to/implement-semantic-chunking-langchain)
- [How to implement streaming responses in AI APIs](https://www.runlocalai.co/learn/how-to/implement-streaming-responses-ai-apis)
- [How to Implement Tool Calling in LangGraph Agents](https://www.runlocalai.co/learn/how-to/implement-tool-calling-langgraph)
- [How to Implement Tool Use in AI Agents](https://www.runlocalai.co/learn/how-to/implement-tool-use-ai-agents)
- [How to implement usage-based billing for AI products](https://www.runlocalai.co/learn/how-to/implement-usage-based-billing-ai)
- [How to Implement Vector Search with Metadata Filtering](https://www.runlocalai.co/learn/how-to/implement-vector-search-metadata-filtering)
- [How to implement web search for AI agents](https://www.runlocalai.co/learn/how-to/implement-web-search-ai-agents)
- [How to import custom GGUF model files into Ollama](https://www.runlocalai.co/learn/how-to/import-custom-gguf-ollama)
- [How to Improve Embedding Quality for Better Retrieval](https://www.runlocalai.co/learn/how-to/improve-embedding-quality-retrieval)
- [How to install Claude Code CLI and authenticate with your Anthropic account](https://www.runlocalai.co/learn/how-to/install-claude-code-cli-authenticate)
- [How to install Continue.dev in VS Code](https://www.runlocalai.co/learn/how-to/install-continue-dev-vscode)
- [How to install CUDA drivers on Ubuntu](https://www.runlocalai.co/learn/how-to/install-cuda-ubuntu)
- [How to install and enable the GitHub Copilot extension in VS Code](https://www.runlocalai.co/learn/how-to/install-enable-github-copilot-vscode)
- [How to install LM Studio on macOS](https://www.runlocalai.co/learn/how-to/install-lm-studio-macos)
- [How to install LM Studio on Windows](https://www.runlocalai.co/learn/how-to/install-lm-studio-windows)
- [How to install NVIDIA Container Toolkit for Docker](https://www.runlocalai.co/learn/how-to/install-nvidia-container-toolkit)
- [How to install Ollama on Linux](https://www.runlocalai.co/learn/how-to/install-ollama-linux)
- [How to install Ollama on macOS](https://www.runlocalai.co/learn/how-to/install-ollama-macos)
- [How to install Ollama on Windows](https://www.runlocalai.co/learn/how-to/install-ollama-windows)
- [How to install Open WebUI with Docker](https://www.runlocalai.co/learn/how-to/install-open-webui-docker)
- [How to install ROCm for AMD GPUs](https://www.runlocalai.co/learn/how-to/install-rocm-amd-gpus)
- [How to install and set up the Cursor IDE AI extension for AI-first coding](https://www.runlocalai.co/learn/how-to/install-setup-cursor-ide-ai-extension)
- [How to install and set up Manus AI on your local development machine](https://www.runlocalai.co/learn/how-to/install-setup-manus-ai)
- [How to install vLLM with pip](https://www.runlocalai.co/learn/how-to/install-vllm-pip)
- [How to instrument an AI agent with OpenTelemetry SDK for automatic trace collection](https://www.runlocalai.co/learn/how-to/instrument-ai-agent-opentelemetry)
- [How to instrument a Python FastAPI AI service with Prometheus metrics](https://www.runlocalai.co/learn/how-to/instrument-fastapi-ai-service-prometheus)
- [How to integrate an AI assistant into your API client library to auto-generate usage examples](https://www.runlocalai.co/learn/how-to/integrate-ai-assistant-api-client-auto-examples)
- [How to integrate AI test generation into a Jenkins CI/CD pipeline using a plugin](https://www.runlocalai.co/learn/how-to/integrate-ai-test-generation-jenkins)
- [How to Integrate FAISS with LangChain](https://www.runlocalai.co/learn/how-to/integrate-faiss-langchain)
- [How to Integrate Web Search Tool in Agents](https://www.runlocalai.co/learn/how-to/integrate-web-search-tool-agents)
- [How to interpret and act on AI-generated code review feedback in a pull request](https://www.runlocalai.co/learn/how-to/interpret-act-on-ai-code-review-feedback)
- [How to create a Kubernetes operator for managing AI model deployments](https://www.runlocalai.co/learn/how-to/kubernetes-operator-ai-model-deployments)
- [How to list all available models on your local Ollama installation](https://www.runlocalai.co/learn/how-to/list-available-models-ollama)
- [How to use llama.cpp with CUDA acceleration](https://www.runlocalai.co/learn/how-to/llama-cpp-cuda-acceleration)
- [How to use LM Studio as a local API server](https://www.runlocalai.co/learn/how-to/lm-studio-local-api-server)
- [How to Load Documents with LangChain Document Loaders](https://www.runlocalai.co/learn/how-to/load-documents-langchain-loaders)
- [How to set up a local development AI stack with LangChain, Postgres, and Weaviate](https://www.runlocalai.co/learn/how-to/local-dev-ai-stack-langchain-postgres-weaviate)
- [How to log conversational context windows for AI agent debugging](https://www.runlocalai.co/learn/how-to/log-conversational-context-windows)
- [How to Manage Agent Context Window Limits](https://www.runlocalai.co/learn/how-to/manage-agent-context-window-limits)
- [How to manage AI model weights with Kubernetes Persistent Volumes](https://www.runlocalai.co/learn/how-to/manage-ai-model-weights-kubernetes-pv)
- [How to manage context overflow for very long conversations](https://www.runlocalai.co/learn/how-to/manage-context-overflow-long-conversations)
- [How to manage models in Open WebUI](https://www.runlocalai.co/learn/how-to/manage-models-open-webui)
- [How to measure and compare prompt variant performance using task-specific evaluation metrics](https://www.runlocalai.co/learn/how-to/measure-compare-prompt-variant-performance)
- [How to measure memory usage during model inference](https://www.runlocalai.co/learn/how-to/measure-memory-usage-inference)
- [How to Monitor Agent Performance Metrics](https://www.runlocalai.co/learn/how-to/monitor-agent-performance-metrics)
- [How to monitor agent token usage and cost](https://www.runlocalai.co/learn/how-to/monitor-agent-token-usage-cost)
- [How to monitor AI agent error rates by error classification](https://www.runlocalai.co/learn/how-to/monitor-ai-agent-error-rates)
- [How to monitor AI agent token usage and cost in real-time using Prometheus counters](https://www.runlocalai.co/learn/how-to/monitor-ai-token-usage-prometheus)
- [How to monitor CPU and GPU memory during inference](https://www.runlocalai.co/learn/how-to/monitor-cpu-gpu-memory-inference)
- [How to monitor GPU utilization for AI inference servers with nvidia-ml-py](https://www.runlocalai.co/learn/how-to/monitor-gpu-utilization-ai-inference)
- [How to monitor LLM response latency percentiles with Prometheus histograms](https://www.runlocalai.co/learn/how-to/monitor-llm-latency-percentiles)
- [How to mount GPU in Docker container](https://www.runlocalai.co/learn/how-to/mount-gpu-docker-container)
- [How to set up a multi-service AI logging stack with Docker Compose](https://www.runlocalai.co/learn/how-to/multi-service-ai-logging-docker-compose)
- [How to build a multi-tenant AI metrics dashboard in Grafana with row-level security](https://www.runlocalai.co/learn/how-to/multi-tenant-ai-dashboard-grafana)
- [How to navigate and edit files using Claude Code's interactive mode](https://www.runlocalai.co/learn/how-to/navigate-edit-files-claude-code-interactive)
- [How to set up network policies for AI service mesh isolation](https://www.runlocalai.co/learn/how-to/network-policies-ai-service-mesh)
- [How to offload models to CPU when GPU memory is insufficient](https://www.runlocalai.co/learn/how-to/offload-models-cpu-insufficient-gpu)
- [How to use Ollama with GPU acceleration (NVIDIA)](https://www.runlocalai.co/learn/how-to/ollama-gpu-acceleration-nvidia)
- [How to optimize batch inference throughput](https://www.runlocalai.co/learn/how-to/optimize-batch-inference-throughput)
- [How to Optimize Chunk Size and Overlap Strategy](https://www.runlocalai.co/learn/how-to/optimize-chunk-size-overlap)
- [How to Optimize FAISS Index for Large Datasets](https://www.runlocalai.co/learn/how-to/optimize-faiss-index-large-datasets)
- [How to optimize llama.cpp inference parameters](https://www.runlocalai.co/learn/how-to/optimize-llama-cpp-parameters)
- [How to Optimize RAG for Low Latency](https://www.runlocalai.co/learn/how-to/optimize-rag-low-latency)
- [How to Optimize Vector Search Query Performance](https://www.runlocalai.co/learn/how-to/optimize-vector-search-query-performance)
- [How to optimize vLLM for throughput](https://www.runlocalai.co/learn/how-to/optimize-vllm-throughput)
- [How to persist Ollama data in Docker](https://www.runlocalai.co/learn/how-to/persist-ollama-data-docker)
- [How to implement pod disruption budgets for AI services during upgrades](https://www.runlocalai.co/learn/how-to/pod-disruption-budgets-ai-upgrades)
- [How to implement predictive autoscaling for AI workloads using historical patterns](https://www.runlocalai.co/learn/how-to/predictive-autoscaling-ai-workloads)
- [How to Preprocess Text for Vector Database Ingestion](https://www.runlocalai.co/learn/how-to/preprocess-text-vector-ingestion)
- [How to process multiple images with a single vision model request](https://www.runlocalai.co/learn/how-to/process-multiple-images-vision-model)
- [How to set up Prometheus alerting rules for AI service degradation](https://www.runlocalai.co/learn/how-to/prometheus-alerting-ai-service-degradation)
- [How to use Prometheus remote_write for long-term AI metrics archival](https://www.runlocalai.co/learn/how-to/prometheus-remote-write-ai-metrics)
- [How to pull a model with Q4_K_M quantization for balanced quality and size](https://www.runlocalai.co/learn/how-to/pull-model-q4-k-m-quantization)
- [How to pull a model with Q5_K_M quantization for detailed responses](https://www.runlocalai.co/learn/how-to/pull-model-q5-k-m-quantization)
- [How to pull a model with Q5_K_S quantization for higher quality](https://www.runlocalai.co/learn/how-to/pull-model-q5-k-s-quantization)
- [How to pull a model with Q8_0 quantization for maximum quality](https://www.runlocalai.co/learn/how-to/pull-model-q8-0-quantization)
- [How to pull models from custom model libraries beyond the default](https://www.runlocalai.co/learn/how-to/pull-models-custom-libraries)
- [How to pull and run DeepSeek MoE models efficiently](https://www.runlocalai.co/learn/how-to/pull-run-deepseek-moe-efficiently)
- [How to pull and run your first open-source LLM using Ollama](https://www.runlocalai.co/learn/how-to/pull-run-first-llm-ollama)
- [How to quantize a model for llama.cpp](https://www.runlocalai.co/learn/how-to/quantize-model-llama-cpp)
- [How to Register and Call Custom Tools in Agents](https://www.runlocalai.co/learn/how-to/register-call-custom-tools-agents)
- [How to configure resource quotas and limit ranges for AI namespaces](https://www.runlocalai.co/learn/how-to/resource-quotas-limit-ranges-ai-namespaces)
- [How to review AI pair programming suggestions for security vulnerabilities before accepting them](https://www.runlocalai.co/learn/how-to/review-ai-suggestions-security-vulnerabilities)
- [How to run batch inference for processing multiple prompts](https://www.runlocalai.co/learn/how-to/run-batch-inference-multiple-prompts)
- [How to run DeepSeek-R1 reasoning models for complex problem-solving](https://www.runlocalai.co/learn/how-to/run-deepseek-r1-reasoning)
- [How to run embedding models for semantic search](https://www.runlocalai.co/learn/how-to/run-embedding-models-semantic-search)
- [How to run inference with llama.cpp server](https://www.runlocalai.co/learn/how-to/run-inference-llama-cpp-server)
- [How to run LLaVA vision model to analyze images](https://www.runlocalai.co/learn/how-to/run-llava-vision-model)
- [How to run Manus AI with custom agent configurations and memory settings](https://www.runlocalai.co/learn/how-to/run-manus-ai-custom-config-memory)
- [How to run a model in the background as a persistent service](https://www.runlocalai.co/learn/how-to/run-model-background-service)
- [How to run multiple models simultaneously on the same system](https://www.runlocalai.co/learn/how-to/run-multiple-models-simultaneously)
- [How to run Ollama in Docker](https://www.runlocalai.co/learn/how-to/run-ollama-docker)
- [How to run quantized models on systems with limited RAM](https://www.runlocalai.co/learn/how-to/run-quantized-models-limited-ram)
- [How to run a specific model version by appending the tag](https://www.runlocalai.co/learn/how-to/run-specific-model-version-tag)
- [How to run a standardized benchmark suite against multiple models](https://www.runlocalai.co/learn/how-to/run-standardized-benchmark-suite)
- [How to run statistical significance tests on A/B prompt test results](https://www.runlocalai.co/learn/how-to/run-statistical-significance-prompt-tests)
- [How to run vLLM in Docker](https://www.runlocalai.co/learn/how-to/run-vllm-docker)
- [How to run vLLM with a HuggingFace model](https://www.runlocalai.co/learn/how-to/run-vllm-huggingface-model)
- [How to run vLLM with an OpenAI-compatible API](https://www.runlocalai.co/learn/how-to/run-vllm-openai-compatible-api)
- [How to scale AI services based on request queue depth with KEDA](https://www.runlocalai.co/learn/how-to/scale-ai-services-queue-depth-keda)
- [How to Scale FAISS Across Multiple Machines](https://www.runlocalai.co/learn/how-to/scale-faiss-across-multiple-machines)
- [How to set GPU layers to optimize memory usage](https://www.runlocalai.co/learn/how-to/set-gpu-layers-optimize-memory)
- [How to set Ollama environment variables](https://www.runlocalai.co/learn/how-to/set-ollama-environment-variables)
- [How to set temperature parameters for creative output](https://www.runlocalai.co/learn/how-to/set-temperature-creative-output)
- [How to set temperature to zero for deterministic responses](https://www.runlocalai.co/learn/how-to/set-temperature-zero-deterministic)
- [How to set up a model switching workflow for different tasks](https://www.runlocalai.co/learn/how-to/set-up-model-switching-workflow)
- [How to set up A/B testing for AI prompts using a traffic splitting framework](https://www.runlocalai.co/learn/how-to/setup-ab-testing-prompts)
- [How to set up agent error recovery and retry logic](https://www.runlocalai.co/learn/how-to/setup-agent-error-recovery-retry)
- [How to set up agent-human collaboration workflows](https://www.runlocalai.co/learn/how-to/setup-agent-human-collaboration)
- [How to set up agent memory with vector databases](https://www.runlocalai.co/learn/how-to/setup-agent-memory-vector-databases)
- [How to set up agent observability with OpenTelemetry](https://www.runlocalai.co/learn/how-to/setup-agent-observability-opentelemetry)
- [How to Set Up Agent Observability and Tracing](https://www.runlocalai.co/learn/how-to/setup-agent-observability-tracing)
- [How to set up agent scheduling with cron and triggers](https://www.runlocalai.co/learn/how-to/setup-agent-scheduling-cron-triggers)
- [How to set up agent tool use with function calling](https://www.runlocalai.co/learn/how-to/setup-agent-tool-use-function-calling)
- [How to set up AI code review automations in GitHub Actions using Claude or GPT models](https://www.runlocalai.co/learn/how-to/setup-ai-code-review-github-actions)
- [How to set up an AI-assisted web scraping pipeline that extracts structured data from HTML](https://www.runlocalai.co/learn/how-to/setup-ai-web-scraping-pipeline)
- [How to set up authentication for local AI endpoints](https://www.runlocalai.co/learn/how-to/setup-authentication-local-ai-endpoints)
- [How to set up auto-scaling for LLM inference](https://www.runlocalai.co/learn/how-to/setup-auto-scaling-llm-inference)
- [How to Set Up Basic LangGraph Agent from Scratch](https://www.runlocalai.co/learn/how-to/setup-basic-langgraph-agent-scratch)
- [How to Set Up Batch Processing for Large Document Sets](https://www.runlocalai.co/learn/how-to/setup-batch-processing-large-documents)
- [How to Set Up ChromaDB from Scratch](https://www.runlocalai.co/learn/how-to/setup-chromadb-scratch)
- [How to set up CI/CD for AI model deployment](https://www.runlocalai.co/learn/how-to/setup-ci-cd-ai-model-deployment)
- [How to set up Continue.dev with LM Studio](https://www.runlocalai.co/learn/how-to/setup-continue-dev-lm-studio)
- [How to Set Up Cross-Encoder Reranking](https://www.runlocalai.co/learn/how-to/setup-cross-encoder-reranking)
- [How to Set Up FAISS Index for Similarity Search](https://www.runlocalai.co/learn/how-to/setup-faiss-index-similarity-search)
- [How to set up GPU memory optimization for inference](https://www.runlocalai.co/learn/how-to/setup-gpu-memory-optimization-inference)
- [How to set up health checks for AI agent services with custom readiness probes](https://www.runlocalai.co/learn/how-to/setup-health-checks-ai-agents)
- [How to set up Manus AI agent](https://www.runlocalai.co/learn/how-to/setup-manus-ai-agent)
- [How to Set Up MCP Server with Standard Tools](https://www.runlocalai.co/learn/how-to/setup-mcp-server-standard-tools)
- [How to set up Metal GPU acceleration on macOS](https://www.runlocalai.co/learn/how-to/setup-metal-gpu-acceleration-macos)
- [How to Set Up Model Fallback Chains (Local to Cloud)](https://www.runlocalai.co/learn/how-to/setup-model-fallback-chains-local-cloud)
- [How to set up model versioning and rollback](https://www.runlocalai.co/learn/how-to/setup-model-versioning-rollback)
- [How to Set Up Multi-Modal RAG with Images](https://www.runlocalai.co/learn/how-to/setup-multi-modal-rag-images)
- [How to set up Open WebUI admin account](https://www.runlocalai.co/learn/how-to/setup-open-webui-admin)
- [How to set up PromptLayer for prompt management](https://www.runlocalai.co/learn/how-to/setup-prompt-layer-prompt-management)
- [How to set up property-based testing by prompting an AI to generate edge cases for your functions](https://www.runlocalai.co/learn/how-to/setup-property-based-testing-ai-edge-cases)
- [How to stop a running model and free up memory](https://www.runlocalai.co/learn/how-to/stop-running-model-free-memory)
- [How to structure prompts to maximize cache hit rates](https://www.runlocalai.co/learn/how-to/structure-prompts-maximize-cache-hits)
- [How to Test Agent Behavior with Unit Tests](https://www.runlocalai.co/learn/how-to/test-agent-behavior-unit-tests)
- [How to test and iterate on system prompt designs using structured evaluation datasets](https://www.runlocalai.co/learn/how-to/test-iterate-system-prompt-designs-evaluation)
- [How to implement token-level logging for LLM prompt auditing and compliance](https://www.runlocalai.co/learn/how-to/token-level-logging-audit-compliance)
- [How to track AI agent conversation state with structured logging and correlation IDs](https://www.runlocalai.co/learn/how-to/track-ai-agent-conversation-state)
- [How to tune an AI model for code review by providing it your team style guide](https://www.runlocalai.co/learn/how-to/tune-ai-model-code-review-style-guide)
- [How to tune reasoning depth in R1 models using parameters](https://www.runlocalai.co/learn/how-to/tune-reasoning-depth-r1-parameters)
- [How to tune the speculation parameters for your hardware setup](https://www.runlocalai.co/learn/how-to/tune-speculation-parameters-hardware)
- [How to tune temperature based on task type](https://www.runlocalai.co/learn/how-to/tune-temperature-by-task-type)
- [How to understand MoE architecture and expert routing](https://www.runlocalai.co/learn/how-to/understand-moe-architecture-routing)
- [How to update an existing model to its latest version](https://www.runlocalai.co/learn/how-to/update-model-latest-version)
- [How to use an AI assistant to analyze a stack trace and pinpoint the root cause of a bug](https://www.runlocalai.co/learn/how-to/use-ai-analyze-stack-trace)
- [How to use an AI assistant to construct SQL queries and data transformation steps for a pipeline](https://www.runlocalai.co/learn/how-to/use-ai-construct-sql-queries-transformations)
- [How to use AI for data quality validation within an ETL pipeline to flag anomalies in ingested records](https://www.runlocalai.co/learn/how-to/use-ai-data-quality-validation-etl)
- [How to use AI to detect and bypass anti-scraping mechanisms on target websites](https://www.runlocalai.co/learn/how-to/use-ai-detect-bypass-anti-scraping)
- [How to use AI to optimize Docker build times by suggesting layer caching improvements in your CI pipeline](https://www.runlocalai.co/learn/how-to/use-ai-optimize-docker-build-times)
- [How to use AI as a pair programmer by setting up real-time code suggestion with Claude in your editor](https://www.runlocalai.co/learn/how-to/use-ai-pair-programmer-real-time-suggestions)
- [How to use AI to transform legacy API response schemas into modern typed structures](https://www.runlocalai.co/learn/how-to/use-ai-transform-legacy-api-schemas)
- [How to use AI to write regression test cases for a bug you just fixed](https://www.runlocalai.co/learn/how-to/use-ai-write-regression-tests)
- [How to use Claude Code CLI for full-stack development](https://www.runlocalai.co/learn/how-to/use-claude-code-cli-fullstack)
- [How to use Claude Code in a read-only reviewing mode for security-sensitive environments](https://www.runlocalai.co/learn/how-to/use-claude-code-read-only-review)
- [How to use Claude Code to review a pull request from the command line](https://www.runlocalai.co/learn/how-to/use-claude-code-review-pull-request)
- [How to use Continue.dev codebase index for fast semantic search across your project](https://www.runlocalai.co/learn/how-to/use-continue-dev-codebase-index-semantic-search)
- [How to use Continue.dev to connect a local codebase to a custom LLM backend](https://www.runlocalai.co/learn/how-to/use-continue-dev-connect-local-codebase-custom-llm)
- [How to use DSPy for prompt optimization](https://www.runlocalai.co/learn/how-to/use-dspy-prompt-optimization)
- [How to Use FAISS for Approximate Nearest Neighbor Search](https://www.runlocalai.co/learn/how-to/use-faiss-approximate-nearest-neighbor)
- [How to use GitHub Copilot Chat for debugging and explaining code in VS Code](https://www.runlocalai.co/learn/how-to/use-github-copilot-chat-debugging)
- [How to use Manus AI to research and compare API options for your project](https://www.runlocalai.co/learn/how-to/use-manus-ai-research-compare-apis)
- [How to Use OpenAI Function Calling with Tools](https://www.runlocalai.co/learn/how-to/use-openai-function-calling-tools)
- [How to use prompt chaining with a code generation pipeline to scaffold a full CRUD API](https://www.runlocalai.co/learn/how-to/use-prompt-chaining-code-generation-crud-api)
- [How to Use Query Rewriting for Better Recall](https://www.runlocalai.co/learn/how-to/use-query-rewriting-better-recall)
- [How to Use Recursive Character Text Splitter](https://www.runlocalai.co/learn/how-to/use-recursive-character-text-splitter)
- [How to Use Semantic Chunking with Embedding Similarity](https://www.runlocalai.co/learn/how-to/use-semantic-chunking-embedding-similarity)
- [How to use a sliding context window strategy to manage long conversations within token limits](https://www.runlocalai.co/learn/how-to/use-sliding-context-window-long-conversations)
- [How to Use Vector Store as Agent Memory](https://www.runlocalai.co/learn/how-to/use-vector-store-agent-memory)
- [How to verify chain-of-thought reasoning in R1 models](https://www.runlocalai.co/learn/how-to/verify-chain-of-thought-r1)
- [How to verify CUDA setup for AI workloads](https://www.runlocalai.co/learn/how-to/verify-cuda-ai-workloads)
- [How to verify model integrity after downloading](https://www.runlocalai.co/learn/how-to/verify-model-integrity-download)
- [How to write YAML or OpenAPI spec documentation for your REST API using an AI assistant](https://www.runlocalai.co/learn/how-to/write-yaml-openapi-spec-ai)

## Courses (60)
- [Advanced Multi-Modal Systems](https://www.runlocalai.co/learn/courses/advanced-multimodal)
- [Advanced NLP with Local Models](https://www.runlocalai.co/learn/courses/advanced-nlp)
- [Advanced Prompt Engineering](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering)
- [Advanced RAG — Chunking, Retrieval, Re-ranking](https://www.runlocalai.co/learn/courses/advanced-rag)
- [Local AI for African Markets](https://www.runlocalai.co/learn/courses/african-markets-local-ai)
- [AI-Powered SaaS Products](https://www.runlocalai.co/learn/courses/ai-powered-saas)
- [AI Products with Local Models](https://www.runlocalai.co/learn/courses/ai-products-local-models)
- [AI Safety and Alignment](https://www.runlocalai.co/learn/courses/ai-safety-alignment)
- [Business Automation with Local AI](https://www.runlocalai.co/learn/courses/business-automation)
- [Capstone: First AI Product](https://www.runlocalai.co/learn/courses/capstone-first-ai-product)
- [Capstone: Full-Stack AI App](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai)
- [Capstone: Research AI System](https://www.runlocalai.co/learn/courses/capstone-research-ai)
- [Local AI for Code Generation](https://www.runlocalai.co/learn/courses/code-generation-local)
- [Content Creation with Local AI](https://www.runlocalai.co/learn/courses/content-creation-ai)
- [Custom Agent Frameworks](https://www.runlocalai.co/learn/courses/custom-agent-frameworks)
- [Custom LLM Architecture Design](https://www.runlocalai.co/learn/courses/custom-llm-architecture)
- [Custom Quantization and Kernels](https://www.runlocalai.co/learn/courses/custom-quantization-kernels)
- [Custom Training Pipelines](https://www.runlocalai.co/learn/courses/custom-training-pipelines)
- [Data Analysis with Local AI](https://www.runlocalai.co/learn/courses/data-analysis-local-ai)
- [DeepSeek R1 and Reasoning Models](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning)
- [Document Processing with Local AI](https://www.runlocalai.co/learn/courses/document-processing)
- [Edge AI: Mobile and IoT](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot)
- [Enterprise-Scale RAG](https://www.runlocalai.co/learn/courses/enterprise-scale-rag)
- [Fine-Tuning with LoRA and QLoRA](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora)
- [First Local Chatbot](https://www.runlocalai.co/learn/courses/first-local-chatbot)
- [Function Calling for Local Models](https://www.runlocalai.co/learn/courses/function-calling)
- [Hardware Planning for Local AI](https://www.runlocalai.co/learn/courses/hardware-planning)
- [Healthcare AI with Local Models](https://www.runlocalai.co/learn/courses/healthcare-ai)
- [Hybrid Local-Cloud AI Architecture](https://www.runlocalai.co/learn/courses/hybrid-local-cloud)
- [Introduction to AI Agents](https://www.runlocalai.co/learn/courses/intro-ai-agents)
- [LangChain for Local AI](https://www.runlocalai.co/learn/courses/langchain-local-ai)
- [LangGraph for Local Agents](https://www.runlocalai.co/learn/courses/langgraph-local-agents)
- [Local AI APIs and Integration](https://www.runlocalai.co/learn/courses/local-ai-apis)
- [Local AI Clusters](https://www.runlocalai.co/learn/courses/local-ai-clusters)
- [Local AI on Linux](https://www.runlocalai.co/learn/courses/local-ai-linux)
- [Local AI on macOS](https://www.runlocalai.co/learn/courses/local-ai-macos)
- [Local AI on Windows](https://www.runlocalai.co/learn/courses/local-ai-windows)
- [MCP Server Implementation](https://www.runlocalai.co/learn/courses/mcp-server-implementation)
- [MLOps for Local AI](https://www.runlocalai.co/learn/courses/mlops-local-ai)
- [Model Compression](https://www.runlocalai.co/learn/courses/model-compression)
- [Model Optimization for Local Inference](https://www.runlocalai.co/learn/courses/model-optimization)
- [Multi-Agent Systems](https://www.runlocalai.co/learn/courses/multi-agent-systems)
- [Multi-Modal AI: Vision and Text](https://www.runlocalai.co/learn/courses/multimodal-vision-text)
- [Ollama — Installation to Mastery](https://www.runlocalai.co/learn/courses/ollama-mastery)
- [OpenCLaw: Building a Personal AI Agent](https://www.runlocalai.co/learn/courses/openclaw-personal-agent)
- [Production Local AI Deployment](https://www.runlocalai.co/learn/courses/production-ai-deployment)
- [Prompt Engineering Fundamentals](https://www.runlocalai.co/learn/courses/prompt-engineering)
- [Python for AI — Zero to Useful](https://www.runlocalai.co/learn/courses/python-for-ai)
- [RAG Evaluation and Metrics](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics)
- [RAG Systems: Part 1](https://www.runlocalai.co/learn/courses/rag-systems-part-1)
- [RAG Systems: Part 2](https://www.runlocalai.co/learn/courses/rag-systems-part-2)
- [RLHF, DPO, and PPO](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo)
- [Local AI for Scientific Research](https://www.runlocalai.co/learn/courses/scientific-research-ai)
- [Security and Privacy for Local AI](https://www.runlocalai.co/learn/courses/security-privacy)
- [Troubleshooting Local AI](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai)
- [Understanding AI Models](https://www.runlocalai.co/learn/courses/understanding-models)
- [Vector Database Internals](https://www.runlocalai.co/learn/courses/vector-database-internals)
- [Vector Stores and Embeddings](https://www.runlocalai.co/learn/courses/vector-stores-embeddings)
- [Voice AI with Local Models](https://www.runlocalai.co/learn/courses/voice-ai-local)
- [What is Local AI — And Why It Matters](https://www.runlocalai.co/learn/courses/what-is-local-ai)

## Course chapters (1180)
- [Beyond Images](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-1-beyond-images)
- [Vision Agents](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-10-vision-agents)
- [Video Agent](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-11-video-agent)
- [Real-Time Processing](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-12-real-time-processing)
- [Streaming Video](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-13-streaming-video)
- [Model Selection for Video](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-14-model-selection-for-video)
- [Hardware Requirements](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-15-hardware-requirements)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-16-performance-optimization)
- [Quantization for Video](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-17-quantization-for-video)
- [Evaluation Metrics](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-18-evaluation-metrics)
- [Benchmarking Multimodal](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-19-benchmarking-multimodal)
- [Video Understanding](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-2-video-understanding)
- [Multi-Modal Training](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-20-multi-modal-training)
- [Synthetic Data](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-21-synthetic-data)
- [Production Deployment](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-22-production-deployment)
- [Multi-Modal Pipeline](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-23-multi-modal-pipeline)
- [Advanced Multimodal Project](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-24-advanced-multimodal-project)
- [Frame Sampling Strategies](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-3-frame-sampling-strategies)
- [Temporal Reasoning](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-4-temporal-reasoning)
- [Video LLMs](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-5-video-llms)
- [Audio-Visual Integration](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-6-audio-visual-integration)
- [Multi-Modal RAG](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-7-multi-modal-rag)
- [Embedding Across Modalities](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-8-embedding-across-modalities)
- [Cross-Modal Retrieval](https://www.runlocalai.co/learn/courses/advanced-multimodal/chapter-9-cross-modal-retrieval)
- [NLP with LLMs vs Traditional Approaches](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-1-nlp-with-llms-vs-traditional-approaches)
- [Query-Focused Summarization](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-10-query-focused-summarization)
- [Emotion and Sentiment](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-11-emotion-and-sentiment)
- [Aspect-Based Sentiment](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-12-aspect-based-sentiment)
- [Topic Modeling](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-13-topic-modeling)
- [Text Clustering](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-14-text-clustering)
- [Data Augmentation](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-15-data-augmentation)
- [Cross-Lingual NLP](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-16-cross-lingual-nlp)
- [Evaluation Metrics](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-17-evaluation-metrics)
- [Advanced NLP Pipeline Project](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-18-advanced-nlp-pipeline-project)
- [Named Entity Recognition](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-2-named-entity-recognition)
- [NER Prompting vs Fine-Tuning](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-3-ner-prompting-vs-fine-tuning)
- [Relation Extraction](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-4-relation-extraction)
- [Multi-Label Classification](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-5-multi-label-classification)
- [Text Classification Pipelines](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-6-text-classification-pipelines)
- [Zero-Shot Classification](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-7-zero-shot-classification)
- [Advanced Summarization](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-8-advanced-summarization)
- [Multi-Document Summarization](https://www.runlocalai.co/learn/courses/advanced-nlp/chapter-9-multi-document-summarization)
- [Beyond Basic Prompting](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-1-beyond-basic-prompting)
- [Automated Prompt Tuning](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-10-automated-prompt-tuning)
- [Prompt Version Control](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-11-prompt-version-control)
- [Prompt Testing Framework](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-12-prompt-testing-framework)
- [Regression Testing](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-13-regression-testing)
- [Cross-Model Portability](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-14-cross-model-portability)
- [Prompt Security](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-15-prompt-security)
- [Cost-Per-Token Optimization](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-16-cost-per-token-optimization)
- [Prompt Compression](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-17-prompt-compression)
- [Prompt Framework Project](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-18-prompt-framework-project)
- [Advanced Chain-of-Thought](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-2-advanced-chain-of-thought)
- [Tree-of-Thought](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-3-tree-of-thought)
- [Self-Consistency](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-4-self-consistency)
- [Prompt Chaining Patterns](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-5-prompt-chaining-patterns)
- [Dynamic Prompt Construction](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-6-dynamic-prompt-construction)
- [DSPy Introduction](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-7-dspy-introduction)
- [DSPy Signatures](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-8-dspy-signatures)
- [DSPy Optimizers](https://www.runlocalai.co/learn/courses/advanced-prompt-engineering/chapter-9-dspy-optimizers)
- [RAG Pipeline Anatomy](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-1-rag-pipeline-anatomy)
- [Local Cross-Encoder Models](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-10-local-cross-encoder-models)
- [Two-Stage Retrieval](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-11-two-stage-retrieval)
- [Query Classification](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-12-query-classification)
- [Query Rewriting](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-13-query-rewriting)
- [Query Decomposition](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-14-query-decomposition)
- [Context Optimization](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-15-context-optimization)
- [Dynamic Context Windows](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-16-dynamic-context-windows)
- [Context Compression](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-17-context-compression)
- [Multi-Modal RAG](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-18-multi-modal-rag)
- [Pipeline Optimization](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-19-pipeline-optimization)
- [Semantic Chunking at Scale](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-2-semantic-chunking-at-scale)
- [Caching Strategies](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-20-caching-strategies)
- [RAGAS Faithfulness](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-21-ragas-faithfulness)
- [RAGAS Answer Relevance](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-22-ragas-answer-relevance)
- [RAGAS Context Precision](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-23-ragas-context-precision)
- [Production RAG Pipeline Project](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-24-production-rag-pipeline-project)
- [Fixed-Size vs Semantic Tradeoffs](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-3-fixed-size-vs-semantic-tradeoffs)
- [Multi-Strategy Retrieval](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-4-multi-strategy-retrieval)
- [Dense Retrieval Deep Dive](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-5-dense-retrieval-deep-dive)
- [Sparse Retrieval BM25](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-6-sparse-retrieval-bm25)
- [Hybrid Search with RRF](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-7-hybrid-search-with-rrf)
- [Weighted Hybrid Strategies](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-8-weighted-hybrid-strategies)
- [Cross-Encoder Setup](https://www.runlocalai.co/learn/courses/advanced-rag/chapter-9-cross-encoder-setup)
- [African AI Opportunity](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-1-african-ai-opportunity)
- [Healthcare for Rural Areas](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-10-healthcare-for-rural-areas)
- [Education Applications](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-11-education-applications)
- [Financial Inclusion](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-12-financial-inclusion)
- [Naira Monetization](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-13-naira-monetization)
- [USSD and SMS Integration](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-14-ussd-and-sms-integration)
- [Community Training](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-15-community-training)
- [Sustainability](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-16-sustainability)
- [Partnership Models](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-17-partnership-models)
- [African Markets Solution Project](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-18-african-markets-solution-project)
- [Offline-First Design](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-2-offline-first-design)
- [Local Language Support](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-3-local-language-support)
- [Yoruba Language Models](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-4-yoruba-language-models)
- [Hausa Language Models](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-5-hausa-language-models)
- [Igbo Language Models](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-6-igbo-language-models)
- [Low-RAM Optimization](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-7-low-ram-optimization)
- [Refurbished Hardware](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-8-refurbished-hardware)
- [Agricultural AI](https://www.runlocalai.co/learn/courses/african-markets-local-ai/chapter-9-agricultural-ai)
- [SaaS Architecture](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-1-saas-architecture)
- [Subscription Billing](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-10-subscription-billing)
- [Paystack Integration](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-11-paystack-integration)
- [Naira Pricing Tiers](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-12-naira-pricing-tiers)
- [Invoice Generation](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-13-invoice-generation)
- [API Rate Limiting](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-14-api-rate-limiting)
- [Quota Management](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-15-quota-management)
- [Analytics Dashboard](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-16-analytics-dashboard)
- [DevOps Automation](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-17-devops-automation)
- [CI/CD for SaaS](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-18-ci-cd-for-saas)
- [Monitoring Multi-Tenant](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-19-monitoring-multi-tenant)
- [Multi-Tenant Design](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-2-multi-tenant-design)
- [Cost Allocation](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-20-cost-allocation)
- [Scaling Strategy](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-21-scaling-strategy)
- [Nigerian Market Strategy](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-22-nigerian-market-strategy)
- [Compliance](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-23-compliance)
- [AI SaaS MVP Project](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-24-ai-saas-mvp-project)
- [Tenant Isolation](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-3-tenant-isolation)
- [User Management](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-4-user-management)
- [Authentication](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-5-authentication)
- [Authorization](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-6-authorization)
- [Usage Metering](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-7-usage-metering)
- [Token Tracking](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-8-token-tracking)
- [API Key Management](https://www.runlocalai.co/learn/courses/ai-powered-saas/chapter-9-api-key-management)
- [Local AI Product Opportunity](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-1-local-ai-product-opportunity)
- [Freemium Strategy](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-10-freemium-strategy)
- [Subscription Design](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-11-subscription-design)
- [Naira Pricing](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-12-naira-pricing)
- [Paystack Integration](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-13-paystack-integration)
- [UX for AI Products](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-14-ux-for-ai-products)
- [Conversational UX](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-15-conversational-ux)
- [Error States](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-16-error-states)
- [Onboarding Flow](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-17-onboarding-flow)
- [Distribution Channels](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-18-distribution-channels)
- [Marketing Strategy](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-19-marketing-strategy)
- [Market Analysis](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-2-market-analysis)
- [Analytics](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-20-analytics)
- [User Feedback Loop](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-21-user-feedback-loop)
- [Iteration](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-22-iteration)
- [Scale Planning](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-23-scale-planning)
- [AI Product Launch Project](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-24-ai-product-launch-project)
- [Competitive Landscape](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-3-competitive-landscape)
- [User Research](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-4-user-research)
- [Problem Definition](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-5-problem-definition)
- [MVP Methodology](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-6-mvp-methodology)
- [Feature Prioritization](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-7-feature-prioritization)
- [Product Roadmap](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-8-product-roadmap)
- [Monetization Models](https://www.runlocalai.co/learn/courses/ai-products-local-models/chapter-9-monetization-models)
- [AI Safety Landscape](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-1-ai-safety-landscape)
- [Feature Attribution](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-10-feature-attribution)
- [Activation Patching](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-11-activation-patching)
- [Bias Detection](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-12-bias-detection)
- [Fairness Metrics](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-13-fairness-metrics)
- [Safety Guardrails](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-14-safety-guardrails)
- [Constitutional AI](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-15-constitutional-ai)
- [Output Filtering](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-16-output-filtering)
- [Evaluation Benchmarks](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-17-evaluation-benchmarks)
- [Safety Evaluation Suite Project](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-18-safety-evaluation-suite-project)
- [Threat Taxonomy](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-2-threat-taxonomy)
- [Adversarial dependableness](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-3-adversarial-dependableness)
- [Jailbreak Attacks](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-4-jailbreak-attacks)
- [Prompt Injection Defense](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-5-prompt-injection-defense)
- [Red Teaming Automation](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-6-red-teaming-automation)
- [Red Team Tools](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-7-red-team-tools)
- [Interpretability Overview](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-8-interpretability-overview)
- [Attention Visualization](https://www.runlocalai.co/learn/courses/ai-safety-alignment/chapter-9-attention-visualization)
- [Business Automation Landscape](https://www.runlocalai.co/learn/courses/business-automation/chapter-1-business-automation-landscape)
- [Approval Workflows](https://www.runlocalai.co/learn/courses/business-automation/chapter-10-approval-workflows)
- [Scheduling Reports](https://www.runlocalai.co/learn/courses/business-automation/chapter-11-scheduling-reports)
- [BI Tool Integration](https://www.runlocalai.co/learn/courses/business-automation/chapter-12-bi-tool-integration)
- [Dashboard Updates](https://www.runlocalai.co/learn/courses/business-automation/chapter-13-dashboard-updates)
- [Alerting Systems](https://www.runlocalai.co/learn/courses/business-automation/chapter-14-alerting-systems)
- [Error Handling](https://www.runlocalai.co/learn/courses/business-automation/chapter-15-error-handling)
- [Audit Logging](https://www.runlocalai.co/learn/courses/business-automation/chapter-16-audit-logging)
- [Security and Compliance](https://www.runlocalai.co/learn/courses/business-automation/chapter-17-security-and-compliance)
- [Business Automation Suite Project](https://www.runlocalai.co/learn/courses/business-automation/chapter-18-business-automation-suite-project)
- [Email Processing Pipeline](https://www.runlocalai.co/learn/courses/business-automation/chapter-2-email-processing-pipeline)
- [Email Classification](https://www.runlocalai.co/learn/courses/business-automation/chapter-3-email-classification)
- [Automated Responses](https://www.runlocalai.co/learn/courses/business-automation/chapter-4-automated-responses)
- [Report Generation](https://www.runlocalai.co/learn/courses/business-automation/chapter-5-report-generation)
- [Data Extraction from Documents](https://www.runlocalai.co/learn/courses/business-automation/chapter-6-data-extraction-from-documents)
- [FAQ Bot](https://www.runlocalai.co/learn/courses/business-automation/chapter-7-faq-bot)
- [Knowledge Base Integration](https://www.runlocalai.co/learn/courses/business-automation/chapter-8-knowledge-base-integration)
- [Workflow Agents](https://www.runlocalai.co/learn/courses/business-automation/chapter-9-workflow-agents)
- [Capstone Overview](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-1-capstone-overview)
- [Documentation](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-10-documentation)
- [Deployment](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-11-deployment)
- [Launch and Iteration](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-12-launch-and-iteration)
- [Product Planning](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-2-product-planning)
- [User Research](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-3-user-research)
- [Architecture Design](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-4-architecture-design)
- [MVP Feature Selection](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-5-mvp-feature-selection)
- [Backend Implementation](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-6-backend-implementation)
- [Frontend Implementation](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-7-frontend-implementation)
- [Integration Testing](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-8-integration-testing)
- [Packaging and Distribution](https://www.runlocalai.co/learn/courses/capstone-first-ai-product/chapter-9-packaging-and-distribution)
- [Capstone Scope](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-1-capstone-scope)
- [Docker Compose Deployment](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-10-docker-compose-deployment)
- [CI/CD Pipeline](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-11-ci-cd-pipeline)
- [Monitoring Setup](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-12-monitoring-setup)
- [Documentation](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-13-documentation)
- [User Guide](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-14-user-guide)
- [API Documentation](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-15-api-documentation)
- [Deployment Runbook](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-16-deployment-runbook)
- [Launch Checklist](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-17-launch-checklist)
- [Full-Stack AI App Project](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-18-full-stack-ai-app-project)
- [Architecture Design](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-2-architecture-design)
- [Model Serving Setup](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-3-model-serving-setup)
- [API Gateway](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-4-api-gateway)
- [Frontend Framework](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-5-frontend-framework)
- [UI/UX Design](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-6-ui-ux-design)
- [Integration Testing](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-7-integration-testing)
- [Performance Testing](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-8-performance-testing)
- [Security Audit](https://www.runlocalai.co/learn/courses/capstone-fullstack-ai/chapter-9-security-audit)
- [Capstone Overview](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-1-capstone-overview)
- [Benchmarking](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-10-benchmarking)
- [Technical Paper Writing](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-11-technical-paper-writing)
- [Paper Structure](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-12-paper-structure)
- [Experimental Results](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-13-experimental-results)
- [Visualization](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-14-visualization)
- [Open-Source Release](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-15-open-source-release)
- [Documentation](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-16-documentation)
- [Community Presentation](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-17-community-presentation)
- [Research System Project](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-18-research-system-project)
- [Research Question](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-2-research-question)
- [Related Work](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-3-related-work)
- [Novel Architecture](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-4-novel-architecture)
- [Implementation](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-5-implementation)
- [Baseline Selection](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-6-baseline-selection)
- [Ablation Study Design](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-7-ablation-study-design)
- [Quantitative Evaluation](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-8-quantitative-evaluation)
- [Qualitative Analysis](https://www.runlocalai.co/learn/courses/capstone-research-ai/chapter-9-qualitative-analysis)
- [Code Generation Landscape](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-1-code-generation-landscape)
- [PR Review with AI](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-10-pr-review-with-ai)
- [Debugging Assistance](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-11-debugging-assistance)
- [Error Explanation](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-12-error-explanation)
- [Repo-Level RAG](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-13-repo-level-rag)
- [Indexing Codebase](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-14-indexing-codebase)
- [Custom Slash Commands](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-15-custom-slash-commands)
- [Multi-Model Setup](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-16-multi-model-setup)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-17-performance-optimization)
- [Code Assistant Project](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-18-code-assistant-project)
- [Continue.dev Installation](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-2-continue-dev-installation)
- [Model Configuration](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-3-model-configuration)
- [Fill-in-Middle Models](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-4-fill-in-middle-models)
- [Autocomplete Setup](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-5-autocomplete-setup)
- [Chat in Editor](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-6-chat-in-editor)
- [Custom Commands](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-7-custom-commands)
- [Context Providers](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-8-context-providers)
- [Code Review Automation](https://www.runlocalai.co/learn/courses/code-generation-local/chapter-9-code-review-automation)
- [AI in Content Workflows](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-1-ai-in-content-workflows)
- [Email Newsletters](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-10-email-newsletters)
- [Batch Content Production](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-11-batch-content-production)
- [Content Calendar Management](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-12-content-calendar-management)
- [AI-Assisted Research](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-13-ai-assisted-research)
- [Plagiarism Checking](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-14-plagiarism-checking)
- [Editorial Review Workflow](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-15-editorial-review-workflow)
- [Content Pipeline Project](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-16-content-pipeline-project)
- [Content Planning with AI](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-2-content-planning-with-ai)
- [Brand Voice Definition](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-3-brand-voice-definition)
- [Writing First Drafts](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-4-writing-first-drafts)
- [Editing with AI](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-5-editing-with-ai)
- [Fact-Checking](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-6-fact-checking)
- [SEO Optimization](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-7-seo-optimization)
- [Blog Post Generation](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-8-blog-post-generation)
- [Social Media Content](https://www.runlocalai.co/learn/courses/content-creation-ai/chapter-9-social-media-content)
- [Why Custom Frameworks?](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-1-why-custom-frameworks)
- [Planning Systems](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-10-planning-systems)
- [Task Planner](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-11-task-planner)
- [Re-planning](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-12-re-planning)
- [Multi-Agent Protocols](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-13-multi-agent-protocols)
- [Agent Communication](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-14-agent-communication)
- [Agent Discovery](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-15-agent-discovery)
- [Observability](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-16-observability)
- [Error Handling](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-17-error-handling)
- [Testing Framework](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-18-testing-framework)
- [Benchmarking](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-19-benchmarking)
- [Agent Runtime Design](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-2-agent-runtime-design)
- [Documentation](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-20-documentation)
- [Package Distribution](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-21-package-distribution)
- [Plugin Architecture](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-22-plugin-architecture)
- [Custom Framework](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-23-custom-framework)
- [Agent Framework Project](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-24-agent-framework-project)
- [Agent Loop](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-3-agent-loop)
- [Tool Registry](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-4-tool-registry)
- [Function Calling Integration](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-5-function-calling-integration)
- [Working Memory](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-6-working-memory)
- [Episodic Memory](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-7-episodic-memory)
- [Semantic Memory](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-8-semantic-memory)
- [Memory Persistence](https://www.runlocalai.co/learn/courses/custom-agent-frameworks/chapter-9-memory-persistence)
- [Transformer Architecture Review](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-1-transformer-architecture-review)
- [Load Balancing](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-10-load-balancing)
- [Mamba State Space Model](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-11-mamba-state-space-model)
- [Selective State Space](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-12-selective-state-space)
- [Comparing Architectures](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-13-comparing-architectures)
- [Custom Attention Patterns](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-14-custom-attention-patterns)
- [Grouped Query Attention](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-15-grouped-query-attention)
- [Sliding Window Attention](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-16-sliding-window-attention)
- [Training Stability](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-17-training-stability)
- [Scaling Laws](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-18-scaling-laws)
- [Architecture Prototyping](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-19-architecture-prototyping)
- [Attention Mechanisms](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-2-attention-mechanisms)
- [Benchmarking Custom Architecture](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-20-benchmarking-custom-architecture)
- [Model Sizing](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-21-model-sizing)
- [Training Infrastructure](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-22-training-infrastructure)
- [Architecture Documentation](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-23-architecture-documentation)
- [Custom Architecture Project](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-24-custom-architecture-project)
- [Multi-Head Attention](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-3-multi-head-attention)
- [FlashAttention Implementation](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-4-flashattention-implementation)
- [Rotary Position Embedding](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-5-rotary-position-embedding)
- [SwiGLU Activation](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-6-swiglu-activation)
- [Transformer Block Design](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-7-transformer-block-design)
- [Mixture of Experts](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-8-mixture-of-experts)
- [Expert Routing](https://www.runlocalai.co/learn/courses/custom-llm-architecture/chapter-9-expert-routing)
- [Quantization Theory](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-1-quantization-theory)
- [Kernel Optimization](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-10-kernel-optimization)
- [TensorRT Plugin Development](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-11-tensorrt-plugin-development)
- [INT8 GEMM](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-12-int8-gemm)
- [FP8 Inference](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-13-fp8-inference)
- [Kernel Benchmarking](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-14-kernel-benchmarking)
- [Quantization Accuracy](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-15-quantization-accuracy)
- [Deploying Custom Kernels](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-16-deploying-custom-kernels)
- [Integration with Runtimes](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-17-integration-with-runtimes)
- [Custom Quantization Project](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-18-custom-quantization-project)
- [Weight Quantization](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-2-weight-quantization)
- [Activation Quantization](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-3-activation-quantization)
- [Calibration Datasets](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-4-calibration-datasets)
- [GGUF Format Deep Dive](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-5-gguf-format-deep-dive)
- [Custom Quant Schemes](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-6-custom-quant-schemes)
- [Mixed Precision](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-7-mixed-precision)
- [CUDA Kernel Basics](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-8-cuda-kernel-basics)
- [Memory Coalescing](https://www.runlocalai.co/learn/courses/custom-quantization-kernels/chapter-9-memory-coalescing)
- [Training Pipeline Overview](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-1-training-pipeline-overview)
- [Custom Training Loop](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-10-custom-training-loop)
- [Loss Functions](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-11-loss-functions)
- [Optimizers and Schedulers](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-12-optimizers-and-schedulers)
- [Hyperparameter Search](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-13-hyperparameter-search)
- [Experiment Tracking with MLflow](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-14-experiment-tracking-with-mlflow)
- [Weights and Biases](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-15-weights-and-biases)
- [Checkpointing](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-16-checkpointing)
- [Pipeline Orchestration](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-17-pipeline-orchestration)
- [Training Pipeline Project](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-18-training-pipeline-project)
- [Data Pipeline Design](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-2-data-pipeline-design)
- [Dataset Curation](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-3-dataset-curation)
- [Data Augmentation](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-4-data-augmentation)
- [Dataset Streaming](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-5-dataset-streaming)
- [Multi-GPU Training](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-6-multi-gpu-training)
- [Data Parallelism](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-7-data-parallelism)
- [Model Parallelism](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-8-model-parallelism)
- [FSDP](https://www.runlocalai.co/learn/courses/custom-training-pipelines/chapter-9-fsdp)
- [AI for Data Analysis](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-1-ai-for-data-analysis)
- [Correlation Analysis](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-10-correlation-analysis)
- [Time Series Analysis](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-11-time-series-analysis)
- [Trend Detection](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-12-trend-detection)
- [Anomaly Detection](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-13-anomaly-detection)
- [Natural Language Insights](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-14-natural-language-insights)
- [Data Storytelling](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-15-data-storytelling)
- [Report Generation](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-16-report-generation)
- [Multi-Source Analysis](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-17-multi-source-analysis)
- [Data Analysis Platform Project](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-18-data-analysis-platform-project)
- [AI-Guided EDA](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-2-ai-guided-eda)
- [Automated Data Profiling](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-3-automated-data-profiling)
- [Text-to-SQL](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-4-text-to-sql)
- [Natural Language Queries](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-5-natural-language-queries)
- [Automated Visualization](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-6-automated-visualization)
- [Chart Recommendations](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-7-chart-recommendations)
- [Statistical Analysis](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-8-statistical-analysis)
- [Hypothesis Testing](https://www.runlocalai.co/learn/courses/data-analysis-local-ai/chapter-9-hypothesis-testing)
- [Reasoning Model Landscape](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-1-reasoning-model-landscape)
- [Training Reasoning Models](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-10-training-reasoning-models)
- [Evaluation of Reasoning](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-11-evaluation-of-reasoning)
- [GSM8K and MATH Benchmarks](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-12-gsm8k-and-math-benchmarks)
- [Multi-Step Reasoning](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-13-multi-step-reasoning)
- [Verification Loops](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-14-verification-loops)
- [R1 with Tools](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-15-r1-with-tools)
- [Production Deployment](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-16-production-deployment)
- [Cost Analysis](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-17-cost-analysis)
- [Reasoning Application Project](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-18-reasoning-application-project)
- [DeepSeek R1 Architecture](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-2-deepseek-r1-architecture)
- [Inference-Time Compute Scaling](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-3-inference-time-compute-scaling)
- [Chain-of-Thought in Reasoning](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-4-chain-of-thought-in-reasoning)
- [R1 Prompting Quirks](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-5-r1-prompting-quirks)
- [Hardware Requirements](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-6-hardware-requirements)
- [Memory Optimization](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-7-memory-optimization)
- [Speculative Decoding for Reasoning](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-8-speculative-decoding-for-reasoning)
- [Distillation of Reasoning](https://www.runlocalai.co/learn/courses/deepseek-r1-reasoning/chapter-9-distillation-of-reasoning)
- [Document Processing Overview](https://www.runlocalai.co/learn/courses/document-processing/chapter-1-document-processing-overview)
- [Table Extraction](https://www.runlocalai.co/learn/courses/document-processing/chapter-10-table-extraction)
- [Batch Processing Architecture](https://www.runlocalai.co/learn/courses/document-processing/chapter-11-batch-processing-architecture)
- [Watch-Folder Automation](https://www.runlocalai.co/learn/courses/document-processing/chapter-12-watch-folder-automation)
- [Processing Pipelines](https://www.runlocalai.co/learn/courses/document-processing/chapter-13-processing-pipelines)
- [Error Handling](https://www.runlocalai.co/learn/courses/document-processing/chapter-14-error-handling)
- [Quality Checks](https://www.runlocalai.co/learn/courses/document-processing/chapter-15-quality-checks)
- [Document Search](https://www.runlocalai.co/learn/courses/document-processing/chapter-16-document-search)
- [Multi-Format Support](https://www.runlocalai.co/learn/courses/document-processing/chapter-17-multi-format-support)
- [Document Pipeline Project](https://www.runlocalai.co/learn/courses/document-processing/chapter-18-document-pipeline-project)
- [PDF Text Extraction](https://www.runlocalai.co/learn/courses/document-processing/chapter-2-pdf-text-extraction)
- [PyMuPDF Deep Dive](https://www.runlocalai.co/learn/courses/document-processing/chapter-3-pymupdf-deep-dive)
- [OCR with Tesseract](https://www.runlocalai.co/learn/courses/document-processing/chapter-4-ocr-with-tesseract)
- [OCR with AI Models](https://www.runlocalai.co/learn/courses/document-processing/chapter-5-ocr-with-ai-models)
- [Image Preprocessing](https://www.runlocalai.co/learn/courses/document-processing/chapter-6-image-preprocessing)
- [Document Classification](https://www.runlocalai.co/learn/courses/document-processing/chapter-7-document-classification)
- [Document Summarization](https://www.runlocalai.co/learn/courses/document-processing/chapter-8-document-summarization)
- [Entity Extraction](https://www.runlocalai.co/learn/courses/document-processing/chapter-9-entity-extraction)
- [Edge AI Overview](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-1-edge-ai-overview)
- [Model Pruning for Edge](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-10-model-pruning-for-edge)
- [Edge Benchmarking](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-11-edge-benchmarking)
- [Power Optimization](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-12-power-optimization)
- [Offline Operation](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-13-offline-operation)
- [Edge-Cloud Hybrid](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-14-edge-cloud-hybrid)
- [Model Updates OTA](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-15-model-updates-ota)
- [Edge Security](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-16-edge-security)
- [Testing on Device](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-17-testing-on-device)
- [Edge Deployment Project](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-18-edge-deployment-project)
- [Raspberry Pi Setup](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-2-raspberry-pi-setup)
- [ONNX Runtime](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-3-onnx-runtime)
- [Model Conversion to ONNX](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-4-model-conversion-to-onnx)
- [TFLite Conversion](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-5-tflite-conversion)
- [Core ML for iOS](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-6-core-ml-for-ios)
- [ML Kit for Android](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-7-ml-kit-for-android)
- [Extreme Quantization](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-8-extreme-quantization)
- [2-bit and 3-bit Quantization](https://www.runlocalai.co/learn/courses/edge-ai-mobile-iot/chapter-9-2-bit-and-3-bit-quantization)
- [Enterprise RAG Challenges](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-1-enterprise-rag-challenges)
- [Row-Level Security](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-10-row-level-security)
- [SLA Monitoring](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-11-sla-monitoring)
- [Latency Budgeting](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-12-latency-budgeting)
- [Semantic Caching](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-13-semantic-caching)
- [Cache Invalidation](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-14-cache-invalidation)
- [Geographic Distribution](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-15-geographic-distribution)
- [Disaster Recovery](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-16-disaster-recovery)
- [Cost Modeling](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-17-cost-modeling)
- [Capacity Planning](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-18-capacity-planning)
- [Performance Benchmarking](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-19-performance-benchmarking)
- [Distributed Architecture](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-2-distributed-architecture)
- [Load Testing](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-20-load-testing)
- [Production Migration](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-21-production-migration)
- [Incident Response](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-22-incident-response)
- [Compliance Auditing](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-23-compliance-auditing)
- [Enterprise RAG Platform Project](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-24-enterprise-rag-platform-project)
- [Microservices Decomposition](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-3-microservices-decomposition)
- [Event Queue with Kafka](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-4-event-queue-with-kafka)
- [Document Ingestion Pipeline](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-5-document-ingestion-pipeline)
- [Real-Time Indexing](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-6-real-time-indexing)
- [Batch vs Streaming Ingestion](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-7-batch-vs-streaming-ingestion)
- [Multi-Modal Enterprise RAG](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-8-multi-modal-enterprise-rag)
- [Document Access Control](https://www.runlocalai.co/learn/courses/enterprise-scale-rag/chapter-9-document-access-control)
- [Why Fine-Tune?](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-1-why-fine-tune)
- [Chat Template](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-10-chat-template)
- [Hugging Face Trainer](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-11-hugging-face-trainer)
- [Training Arguments](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-12-training-arguments)
- [Gradient Checkpointing](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-13-gradient-checkpointing)
- [Training Loop](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-14-training-loop)
- [Monitoring Training](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-15-monitoring-training)
- [Evaluation](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-16-evaluation)
- [Adapter Management](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-17-adapter-management)
- [Merging Adapters](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-18-merging-adapters)
- [GGUF Conversion](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-19-gguf-conversion)
- [Fine-Tuning vs RAG](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-2-fine-tuning-vs-rag)
- [Inference with Fine-Tuned Models](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-20-inference-with-fine-tuned-models)
- [Catastrophic Forgetting](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-21-catastrophic-forgetting)
- [Multi-Task Fine-Tuning](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-22-multi-task-fine-tuning)
- [Domain Adaptation](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-23-domain-adaptation)
- [Domain Fine-Tune Project](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-24-domain-fine-tune-project)
- [LoRA Theory](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-3-lora-theory)
- [Rank Selection](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-4-rank-selection)
- [Target Modules](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-5-target-modules)
- [QLoRA: Quantized LoRA](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-6-qlora-quantized-lora)
- [4-bit NormalFloat](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-7-4-bit-normalfloat)
- [Dataset Preparation](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-8-dataset-preparation)
- [Data Formatting](https://www.runlocalai.co/learn/courses/finetuning-lora-qlora/chapter-9-data-formatting)
- [Chatbot Architecture](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-1-chatbot-architecture)
- [Multiple Model Selection](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-10-multiple-model-selection)
- [Error Handling](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-11-error-handling)
- [UI Polish](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-12-ui-polish)
- [LAN Deployment](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-13-lan-deployment)
- [Docker Deployment](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-14-docker-deployment)
- [Chatbot Project Wrap-up](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-15-chatbot-project-wrap-up)
- [FastAPI Backend Setup](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-2-fastapi-backend-setup)
- [Ollama Integration](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-3-ollama-integration)
- [Streaming Responses](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-4-streaming-responses)
- [HTML Frontend Basics](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-5-html-frontend-basics)
- [JavaScript EventSource](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-6-javascript-eventsource)
- [Conversation Memory](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-7-conversation-memory)
- [Session Management](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-8-session-management)
- [Personality Configuration](https://www.runlocalai.co/learn/courses/first-local-chatbot/chapter-9-personality-configuration)
- [Function Calling Overview](https://www.runlocalai.co/learn/courses/function-calling/chapter-1-function-calling-overview)
- [Error Recovery](https://www.runlocalai.co/learn/courses/function-calling/chapter-10-error-recovery)
- [Retry Logic](https://www.runlocalai.co/learn/courses/function-calling/chapter-11-retry-logic)
- [Streaming with Tools](https://www.runlocalai.co/learn/courses/function-calling/chapter-12-streaming-with-tools)
- [LangChain Tools Integration](https://www.runlocalai.co/learn/courses/function-calling/chapter-13-langchain-tools-integration)
- [Production Monitoring](https://www.runlocalai.co/learn/courses/function-calling/chapter-14-production-monitoring)
- [Rate Limiting](https://www.runlocalai.co/learn/courses/function-calling/chapter-15-rate-limiting)
- [Tool Security](https://www.runlocalai.co/learn/courses/function-calling/chapter-16-tool-security)
- [Testing Function Calling](https://www.runlocalai.co/learn/courses/function-calling/chapter-17-testing-function-calling)
- [Tool Ecosystem Project](https://www.runlocalai.co/learn/courses/function-calling/chapter-18-tool-ecosystem-project)
- [JSON Schema for Tools](https://www.runlocalai.co/learn/courses/function-calling/chapter-2-json-schema-for-tools)
- [Defining Tool Functions](https://www.runlocalai.co/learn/courses/function-calling/chapter-3-defining-tool-functions)
- [Ollama Function Calling](https://www.runlocalai.co/learn/courses/function-calling/chapter-4-ollama-function-calling)
- [vLLM Function Calling](https://www.runlocalai.co/learn/courses/function-calling/chapter-5-vllm-function-calling)
- [Single Tool Execution](https://www.runlocalai.co/learn/courses/function-calling/chapter-6-single-tool-execution)
- [Multi-Tool Orchestration](https://www.runlocalai.co/learn/courses/function-calling/chapter-7-multi-tool-orchestration)
- [Parallel Tool Calls](https://www.runlocalai.co/learn/courses/function-calling/chapter-8-parallel-tool-calls)
- [Tool Output Handling](https://www.runlocalai.co/learn/courses/function-calling/chapter-9-tool-output-handling)
- [VRAM is Everything](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-1-vram-is-everything)
- [Motherboard and PSU](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-10-motherboard-and-psu)
- [External GPU Enclosures](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-11-external-gpu-enclosures)
- [Cloud GPU Fallback](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-12-cloud-gpu-fallback)
- [Budget Build: Entry-Level Under $500](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-13-budget-build-entry-level-under-500)
- [Budget Build: Mid-Range $800-1200](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-14-budget-build-mid-range-800-1200)
- [Budget Build: High-Performance $2000-3000](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-15-budget-build-high-performance-2000-3000)
- [Used GPU Buying Guide](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-16-used-gpu-buying-guide)
- [Future-Proofing](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-17-future-proofing)
- [Multi-GPU Setup](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-18-multi-gpu-setup)
- [Hardware Benchmarking](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-19-hardware-benchmarking)
- [Calculating VRAM Needs](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-2-calculating-vram-needs)
- [Personal Hardware Plan Project](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-20-personal-hardware-plan-project)
- [GPU Selection: Budget Tier](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-3-gpu-selection-budget-tier)
- [GPU Selection: Mid-Range](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-4-gpu-selection-mid-range)
- [GPU Selection: High-End](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-5-gpu-selection-high-end)
- [CPU-Only Inference](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-6-cpu-only-inference)
- [AMD ROCm Compatibility](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-7-amd-rocm-compatibility)
- [Apple Silicon Deep Dive](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-8-apple-silicon-deep-dive)
- [System RAM Benefits](https://www.runlocalai.co/learn/courses/hardware-planning/chapter-9-system-ram-benefits)
- [Healthcare AI Landscape](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-1-healthcare-ai-landscape)
- [Medical Imaging Analysis](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-10-medical-imaging-analysis)
- [Radiology Report Drafting](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-11-radiology-report-drafting)
- [Patient Communication](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-12-patient-communication)
- [Appointment Scheduling](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-13-appointment-scheduling)
- [Symptom Checking](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-14-symptom-checking)
- [Telemedicine Integration](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-15-telemedicine-integration)
- [Privacy-Preserving AI](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-16-privacy-preserving-ai)
- [Clinical Validation](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-17-clinical-validation)
- [Medical Document Assistant Project](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-18-medical-document-assistant-project)
- [HIPAA Compliance](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-2-hipaa-compliance)
- [NDPR for Nigerian Healthcare](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-3-ndpr-for-nigerian-healthcare)
- [De-identification of PHI](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-4-de-identification-of-phi)
- [Clinical Note Processing](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-5-clinical-note-processing)
- [SOAP Note Generation](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-6-soap-note-generation)
- [Medical Coding Assistance](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-7-medical-coding-assistance)
- [Decision Support Systems](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-8-decision-support-systems)
- [Drug Interaction Checking](https://www.runlocalai.co/learn/courses/healthcare-ai/chapter-9-drug-interaction-checking)
- [Why Hybrid?](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-1-why-hybrid)
- [Fallback Chains](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-10-fallback-chains)
- [Local-First Strategy](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-11-local-first-strategy)
- [Cloud-Fallback Strategy](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-12-cloud-fallback-strategy)
- [Cross-Tier Monitoring](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-13-cross-tier-monitoring)
- [Cost Analytics](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-14-cost-analytics)
- [Usage Tracking](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-15-usage-tracking)
- [Security Boundaries](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-16-security-boundaries)
- [Performance Benchmarking](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-17-performance-benchmarking)
- [Hybrid Gateway Project](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-18-hybrid-gateway-project)
- [Routing Policies](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-2-routing-policies)
- [Rule-Based Routing](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-3-rule-based-routing)
- [Model Router Architecture](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-4-model-router-architecture)
- [Cost-Aware Selection](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-5-cost-aware-selection)
- [Latency-Aware Routing](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-6-latency-aware-routing)
- [Privacy-Preserving Routing](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-7-privacy-preserving-routing)
- [Unified API Layer](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-8-unified-api-layer)
- [OpenAI-Compatible Gateway](https://www.runlocalai.co/learn/courses/hybrid-local-cloud/chapter-9-openai-compatible-gateway)
- [What is an AI Agent?](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-1-what-is-an-ai-agent)
- [Agent Memory](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-10-agent-memory)
- [Conversation History](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-11-conversation-history)
- [Agent Planning](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-12-agent-planning)
- [Task Decomposition](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-13-task-decomposition)
- [Error Recovery](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-14-error-recovery)
- [Agent Evaluation](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-15-agent-evaluation)
- [Agent Project: Research Assistant](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-16-agent-project-research-assistant)
- [Agent Architecture](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-2-agent-architecture)
- [ReAct Pattern](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-3-react-pattern)
- [Tool Definition](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-4-tool-definition)
- [Function Calling in Ollama](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-5-function-calling-in-ollama)
- [Function Calling in vLLM](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-6-function-calling-in-vllm)
- [Building a Web Search Tool](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-7-building-a-web-search-tool)
- [Building a Calculator Tool](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-8-building-a-calculator-tool)
- [Multi-Tool Agents](https://www.runlocalai.co/learn/courses/intro-ai-agents/chapter-9-multi-tool-agents)
- [What is LangChain?](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-1-what-is-langchain)
- [Memory: Summary](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-10-memory-summary)
- [Memory: Vector Store](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-11-memory-vector-store)
- [Document Loaders](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-12-document-loaders)
- [Text Splitters](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-13-text-splitters)
- [Simple RAG Pipeline](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-14-simple-rag-pipeline)
- [RetrievalQA Chain](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-15-retrievalqa-chain)
- [Streaming with LangChain](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-16-streaming-with-langchain)
- [LangChain Callbacks](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-17-langchain-callbacks)
- [LangChain Evaluation](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-18-langchain-evaluation)
- [Ollama LLM Integration](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-2-ollama-llm-integration)
- [Prompt Templates](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-3-prompt-templates)
- [ChatPromptTemplate](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-4-chatprompttemplate)
- [LLMChain Basics](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-5-llmchain-basics)
- [Sequential Chains](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-6-sequential-chains)
- [Router Chains](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-7-router-chains)
- [LangChain Output Parsers](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-8-langchain-output-parsers)
- [Memory: ConversationBuffer](https://www.runlocalai.co/learn/courses/langchain-local-ai/chapter-9-memory-conversationbuffer)
- [What is LangGraph?](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-1-what-is-langgraph)
- [Supervisor Agent](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-10-supervisor-agent)
- [Specialized Worker Agents](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-11-specialized-worker-agents)
- [Agent Communication](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-12-agent-communication)
- [Subgraphs](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-13-subgraphs)
- [Error Handling](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-14-error-handling)
- [Persistence](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-15-persistence)
- [Streaming Agent Output](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-16-streaming-agent-output)
- [LangGraph vs LangChain](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-17-langgraph-vs-langchain)
- [Multi-Agent Research Team Project](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-18-multi-agent-research-team-project)
- [StateGraph Basics](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-2-stategraph-basics)
- [Nodes and Edges](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-3-nodes-and-edges)
- [State Management](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-4-state-management)
- [Tool-Calling Agent in LangGraph](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-5-tool-calling-agent-in-langgraph)
- [Conditional Edges](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-6-conditional-edges)
- [Human-in-the-Loop](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-7-human-in-the-loop)
- [Checkpointing](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-8-checkpointing)
- [Multi-Agent Teams](https://www.runlocalai.co/learn/courses/langgraph-local-agents/chapter-9-multi-agent-teams)
- [API Design Principles](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-1-api-design-principles)
- [Request Logging](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-10-request-logging)
- [Error Responses](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-11-error-responses)
- [Health Checks](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-12-health-checks)
- [OpenAPI Documentation](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-13-openapi-documentation)
- [Client Libraries](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-14-client-libraries)
- [Load Testing](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-15-load-testing)
- [Caching Layer](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-16-caching-layer)
- [Production Hardening](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-17-production-hardening)
- [API Gateway Project](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-18-api-gateway-project)
- [OpenAI API Format](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-2-openai-api-format)
- [FastAPI Basics](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-3-fastapi-basics)
- [Chat Completions Endpoint](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-4-chat-completions-endpoint)
- [Streaming with SSE](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-5-streaming-with-sse)
- [API Key Authentication](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-6-api-key-authentication)
- [Rate Limiting](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-7-rate-limiting)
- [Multi-Model Gateway](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-8-multi-model-gateway)
- [Model Routing](https://www.runlocalai.co/learn/courses/local-ai-apis/chapter-9-model-routing)
- [Why Cluster?](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-1-why-cluster)
- [NVIDIA GPU Operator](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-10-nvidia-gpu-operator)
- [Slurm for AI](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-11-slurm-for-ai)
- [Model Repository](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-12-model-repository)
- [Load Balancing](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-13-load-balancing)
- [Cluster Monitoring](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-14-cluster-monitoring)
- [Fault Tolerance](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-15-fault-tolerance)
- [Cost Analysis](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-16-cost-analysis)
- [Cluster Benchmarking](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-17-cluster-benchmarking)
- [Local AI Cluster Project](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-18-local-ai-cluster-project)
- [Cluster Topology](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-2-cluster-topology)
- [Network Requirements](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-3-network-requirements)
- [Shared Storage](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-4-shared-storage)
- [Tensor Parallelism](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-5-tensor-parallelism)
- [Pipeline Parallelism](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-6-pipeline-parallelism)
- [vLLM Distributed Serving](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-7-vllm-distributed-serving)
- [Multi-Node Inference](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-8-multi-node-inference)
- [Kubernetes Cluster Setup](https://www.runlocalai.co/learn/courses/local-ai-clusters/chapter-9-kubernetes-cluster-setup)
- [Why Linux for AI](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-1-why-linux-for-ai)
- [Docker Compose AI Stack](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-10-docker-compose-ai-stack)
- [Kernel Tuning for AI](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-11-kernel-tuning-for-ai)
- [Firewall and Security](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-12-firewall-and-security)
- [Remote Access Setup](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-13-remote-access-setup)
- [Monitoring AI Services](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-14-monitoring-ai-services)
- [Linux AI Workstation Project](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-15-linux-ai-workstation-project)
- [NVIDIA Driver Installation](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-2-nvidia-driver-installation)
- [CUDA Toolkit Setup](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-3-cuda-toolkit-setup)
- [ROCm for AMD GPUs](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-4-rocm-for-amd-gpus)
- [Ollama on Linux](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-5-ollama-on-linux)
- [llama.cpp from Source](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-6-llama-cpp-from-source)
- [Systemd Service for AI](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-7-systemd-service-for-ai)
- [Headless Server Setup](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-8-headless-server-setup)
- [Docker on Linux for AI](https://www.runlocalai.co/learn/courses/local-ai-linux/chapter-9-docker-on-linux-for-ai)
- [macOS AI Landscape](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-1-macos-ai-landscape)
- [Activity Monitor for AI](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-10-activity-monitor-for-ai)
- [Running Docker on Mac](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-11-running-docker-on-mac)
- [LM Studio on macOS](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-12-lm-studio-on-macos)
- [Open WebUI on macOS](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-13-open-webui-on-macos)
- [Troubleshooting macOS AI](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-14-troubleshooting-macos-ai)
- [macOS AI Workflows](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-15-macos-ai-workflows)
- [Apple Silicon Architecture](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-2-apple-silicon-architecture)
- [Ollama on macOS](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-3-ollama-on-macos)
- [Metal GPU Acceleration](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-4-metal-gpu-acceleration)
- [MLX Framework](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-5-mlx-framework)
- [MLX vs Ollama vs llama.cpp](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-6-mlx-vs-ollama-vs-llama-cpp)
- [Unified Memory Explained](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-7-unified-memory-explained)
- [Mac Model Selection Guide](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-8-mac-model-selection-guide)
- [Performance Tuning](https://www.runlocalai.co/learn/courses/local-ai-macos/chapter-9-performance-tuning)
- [Introduction to Local AI on Windows](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-1-introduction-to-local-ai-on-windows)
- [Path Configuration](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-10-path-configuration)
- [Antivirus Considerations](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-11-antivirus-considerations)
- [WSL2 Troubleshooting](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-12-wsl2-troubleshooting)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-13-performance-optimization)
- [Open WebUI on Windows](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-14-open-webui-on-windows)
- [Windows AI Tools Ecosystem](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-15-windows-ai-tools-ecosystem)
- [WSL2 Installation and Configuration](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-2-wsl2-installation-and-configuration)
- [WSL2 Memory and Performance Tuning](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-3-wsl2-memory-and-performance-tuning)
- [NVIDIA CUDA Setup with WSL2](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-4-nvidia-cuda-setup-with-wsl2)
- [Docker Desktop for Windows](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-5-docker-desktop-for-windows)
- [Running AI Containers in Docker](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-6-running-ai-containers-in-docker)
- [Native Ollama on Windows](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-7-native-ollama-on-windows)
- [Managing Models with CLI](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-8-managing-models-with-cli)
- [LM Studio GUI Alternative](https://www.runlocalai.co/learn/courses/local-ai-windows/chapter-9-lm-studio-gui-alternative)
- [What is MCP?](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-1-what-is-mcp)
- [API Integration Server](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-10-api-integration-server)
- [SSE Transport](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-11-sse-transport)
- [Streamable HTTP Transport](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-12-streamable-http-transport)
- [Security Best Practices](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-13-security-best-practices)
- [Authentication](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-14-authentication)
- [Authorization Scopes](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-15-authorization-scopes)
- [Claude Code Integration](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-16-claude-code-integration)
- [Debugging MCP Servers](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-17-debugging-mcp-servers)
- [Testing MCP](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-18-testing-mcp)
- [Error Handling](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-19-error-handling)
- [MCP Specification Overview](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-2-mcp-specification-overview)
- [Logging and Monitoring](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-20-logging-and-monitoring)
- [Multi-Server Orchestration](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-21-multi-server-orchestration)
- [Custom MCP Tool Suite Project](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-22-custom-mcp-tool-suite-project)
- [Architecture: Client vs Server](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-3-architecture-client-vs-server)
- [Python SDK Setup](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-4-python-sdk-setup)
- [Resources in MCP](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-5-resources-in-mcp)
- [Tools in MCP](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-6-tools-in-mcp)
- [Prompts in MCP](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-7-prompts-in-mcp)
- [File System Server](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-8-file-system-server)
- [Database Query Server](https://www.runlocalai.co/learn/courses/mcp-server-implementation/chapter-9-database-query-server)
- [MLOps Overview](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-1-mlops-overview)
- [Model Validation Gates](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-10-model-validation-gates)
- [Data Validation](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-11-data-validation)
- [Model Validation](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-12-model-validation)
- [Drift Detection](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-13-drift-detection)
- [Data Drift](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-14-data-drift)
- [Model Drift](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-15-model-drift)
- [CI/CD for ML](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-16-ci-cd-for-ml)
- [Pipeline as Code](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-17-pipeline-as-code)
- [GitOps for Models](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-18-gitops-for-models)
- [Infrastructure as Code](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-19-infrastructure-as-code)
- [Experiment Tracking](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-2-experiment-tracking)
- [Ansible for AI](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-20-ansible-for-ai)
- [Monitoring and Alerting](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-21-monitoring-and-alerting)
- [Model Governance](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-22-model-governance)
- [Audit Trails](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-23-audit-trails)
- [MLOps Pipeline Project](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-24-mlops-pipeline-project)
- [MLflow Setup](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-3-mlflow-setup)
- [MLflow Tracking Server](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-4-mlflow-tracking-server)
- [Model Registry](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-5-model-registry)
- [Model Versioning](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-6-model-versioning)
- [Pipeline Orchestration](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-7-pipeline-orchestration)
- [Airflow for AI](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-8-airflow-for-ai)
- [Prefect for AI](https://www.runlocalai.co/learn/courses/mlops-local-ai/chapter-9-prefect-for-ai)
- [Why Compression?](https://www.runlocalai.co/learn/courses/model-compression/chapter-1-why-compression)
- [Prune-Distill-Quantize Pipeline](https://www.runlocalai.co/learn/courses/model-compression/chapter-10-prune-distill-quantize-pipeline)
- [Combined Compression](https://www.runlocalai.co/learn/courses/model-compression/chapter-11-combined-compression)
- [Pareto Frontier Analysis](https://www.runlocalai.co/learn/courses/model-compression/chapter-12-pareto-frontier-analysis)
- [Accuracy vs Size Tradeoffs](https://www.runlocalai.co/learn/courses/model-compression/chapter-13-accuracy-vs-size-tradeoffs)
- [Hardware-Aware Compression](https://www.runlocalai.co/learn/courses/model-compression/chapter-14-hardware-aware-compression)
- [Compression Benchmarking](https://www.runlocalai.co/learn/courses/model-compression/chapter-15-compression-benchmarking)
- [Deploying Compressed Models](https://www.runlocalai.co/learn/courses/model-compression/chapter-16-deploying-compressed-models)
- [Compression Evaluation](https://www.runlocalai.co/learn/courses/model-compression/chapter-17-compression-evaluation)
- [Model Compression Pipeline Project](https://www.runlocalai.co/learn/courses/model-compression/chapter-18-model-compression-pipeline-project)
- [Pruning: Unstructured](https://www.runlocalai.co/learn/courses/model-compression/chapter-2-pruning-unstructured)
- [Pruning: Structured](https://www.runlocalai.co/learn/courses/model-compression/chapter-3-pruning-structured)
- [Magnitude Pruning](https://www.runlocalai.co/learn/courses/model-compression/chapter-4-magnitude-pruning)
- [Movement Pruning](https://www.runlocalai.co/learn/courses/model-compression/chapter-5-movement-pruning)
- [Knowledge Distillation](https://www.runlocalai.co/learn/courses/model-compression/chapter-6-knowledge-distillation)
- [Teacher-Student Setup](https://www.runlocalai.co/learn/courses/model-compression/chapter-7-teacher-student-setup)
- [Distillation Loss Functions](https://www.runlocalai.co/learn/courses/model-compression/chapter-8-distillation-loss-functions)
- [Distillation at Scale](https://www.runlocalai.co/learn/courses/model-compression/chapter-9-distillation-at-scale)
- [Why Optimize?](https://www.runlocalai.co/learn/courses/model-optimization/chapter-1-why-optimize)
- [PagedAttention](https://www.runlocalai.co/learn/courses/model-optimization/chapter-10-pagedattention)
- [vLLM Optimization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-11-vllm-optimization)
- [TensorRT-LLM](https://www.runlocalai.co/learn/courses/model-optimization/chapter-12-tensorrt-llm)
- [Pruning: Structured vs Unstructured](https://www.runlocalai.co/learn/courses/model-optimization/chapter-13-pruning-structured-vs-unstructured)
- [Attention Sink](https://www.runlocalai.co/learn/courses/model-optimization/chapter-14-attention-sink)
- [KV Cache Optimization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-15-kv-cache-optimization)
- [Prompt Caching](https://www.runlocalai.co/learn/courses/model-optimization/chapter-16-prompt-caching)
- [Batch Optimization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-17-batch-optimization)
- [End-to-End Optimization Project](https://www.runlocalai.co/learn/courses/model-optimization/chapter-18-end-to-end-optimization-project)
- [Quantization Formats Compared](https://www.runlocalai.co/learn/courses/model-optimization/chapter-2-quantization-formats-compared)
- [GPTQ Quantization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-3-gptq-quantization)
- [AWQ Quantization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-4-awq-quantization)
- [GGUF Quantization](https://www.runlocalai.co/learn/courses/model-optimization/chapter-5-gguf-quantization)
- [Quantization Quality Tradeoffs](https://www.runlocalai.co/learn/courses/model-optimization/chapter-6-quantization-quality-tradeoffs)
- [Speculative Decoding](https://www.runlocalai.co/learn/courses/model-optimization/chapter-7-speculative-decoding)
- [Draft Models](https://www.runlocalai.co/learn/courses/model-optimization/chapter-8-draft-models)
- [FlashAttention](https://www.runlocalai.co/learn/courses/model-optimization/chapter-9-flashattention)
- [Why Multi-Agent?](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-1-why-multi-agent)
- [Tool Sharing](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-10-tool-sharing)
- [Conflict Resolution](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-11-conflict-resolution)
- [Consensus Mechanisms](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-12-consensus-mechanisms)
- [Agent Observability](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-13-agent-observability)
- [Agent Tracing](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-14-agent-tracing)
- [Performance Metrics](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-15-performance-metrics)
- [Error Recovery](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-16-error-recovery)
- [Scaling Agents](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-17-scaling-agents)
- [Security Considerations](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-18-security-considerations)
- [Multi-Agent Testing](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-19-multi-agent-testing)
- [Orchestrator-Worker Pattern](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-2-orchestrator-worker-pattern)
- [Production Deployment](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-20-production-deployment)
- [Multi-Agent Content Team](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-21-multi-agent-content-team)
- [Research Agent Team](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-22-research-agent-team)
- [Customer Support Agents](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-23-customer-support-agents)
- [Multi-Agent Platform Project](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-24-multi-agent-platform-project)
- [Debate Pattern](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-3-debate-pattern)
- [Agent Communication Protocols](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-4-agent-communication-protocols)
- [Message Passing](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-5-message-passing)
- [Shared State](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-6-shared-state)
- [Supervisor Agents](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-7-supervisor-agents)
- [Specialized Agent Roles](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-8-specialized-agent-roles)
- [Task Decomposition](https://www.runlocalai.co/learn/courses/multi-agent-systems/chapter-9-task-decomposition)
- [Multi-Modal Models Overview](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-1-multi-modal-models-overview)
- [Streaming with Vision](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-10-streaming-with-vision)
- [Vision Agents](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-11-vision-agents)
- [Multi-Modal RAG](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-12-multi-modal-rag)
- [Image Embeddings](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-13-image-embeddings)
- [CLIP Models](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-14-clip-models)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-15-performance-optimization)
- [Quantization for Vision](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-16-quantization-for-vision)
- [Multi-Modal Evaluation](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-17-multi-modal-evaluation)
- [Vision Analysis System Project](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-18-vision-analysis-system-project)
- [LLaVA Installation](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-2-llava-installation)
- [BakLLaVA Setup](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-3-bakllava-setup)
- [Image Captioning](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-4-image-captioning)
- [Visual Question Answering](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-5-visual-question-answering)
- [Chart and Diagram Understanding](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-6-chart-and-diagram-understanding)
- [OCR with Vision Models](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-7-ocr-with-vision-models)
- [Document Image Analysis](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-8-document-image-analysis)
- [Batch Image Processing](https://www.runlocalai.co/learn/courses/multimodal-vision-text/chapter-9-batch-image-processing)
- [What is Ollama?](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-1-what-is-ollama)
- [Concurrent Requests](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-10-concurrent-requests)
- [Model Management Automation](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-11-model-management-automation)
- [Ollama as Systemd Service](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-12-ollama-as-systemd-service)
- [Docker Deployment](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-13-docker-deployment)
- [Docker Compose Stack](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-14-docker-compose-stack)
- [Open WebUI Integration](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-15-open-webui-integration)
- [Continue.dev Integration](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-16-continue-dev-integration)
- [GPU Not Detected](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-17-gpu-not-detected)
- [OOM Errors](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-18-oom-errors)
- [Slow Inference Debugging](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-19-slow-inference-debugging)
- [Installation by OS](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-2-installation-by-os)
- [Model Download Failures](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-20-model-download-failures)
- [First Model](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-3-first-model)
- [Multiple Models](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-4-multiple-models)
- [Modelfiles: Customizing Models](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-5-modelfiles-customizing-models)
- [Ollama REST API](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-6-ollama-rest-api)
- [Ollama Python Client](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-7-ollama-python-client)
- [GPU vs CPU Inference](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-8-gpu-vs-cpu-inference)
- [Performance Tuning](https://www.runlocalai.co/learn/courses/ollama-mastery/chapter-9-performance-tuning)
- [OpenCLaw Vision](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-1-openclaw-vision)
- [Plugin API](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-10-plugin-api)
- [Cron Scheduling](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-11-cron-scheduling)
- [Scheduled Tasks](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-12-scheduled-tasks)
- [Learning from Feedback](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-13-learning-from-feedback)
- [User Preference Learning](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-14-user-preference-learning)
- [Conversation Summaries](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-15-conversation-summaries)
- [Notification System](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-16-notification-system)
- [Web Interface](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-17-web-interface)
- [Security Model](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-18-security-model)
- [Privacy by Design](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-19-privacy-by-design)
- [Always-On Architecture](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-2-always-on-architecture)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-20-performance-optimization)
- [Power Management](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-21-power-management)
- [Plugin Development SDK](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-22-plugin-development-sdk)
- [Testing and Debugging](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-23-testing-and-debugging)
- [OpenCLaw Implementation Project](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-24-openclaw-implementation-project)
- [Background Service](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-3-background-service)
- [Persistent Memory](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-4-persistent-memory)
- [SQLite for Short-Term](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-5-sqlite-for-short-term)
- [Vector Store for Long-Term](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-6-vector-store-for-long-term)
- [Memory Consolidation](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-7-memory-consolidation)
- [Tool Integration](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-8-tool-integration)
- [Plugin System](https://www.runlocalai.co/learn/courses/openclaw-personal-agent/chapter-9-plugin-system)
- [Production Mindset](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-1-production-mindset)
- [Services and Ingress](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-10-services-and-ingress)
- [ConfigMaps and Secrets](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-11-configmaps-and-secrets)
- [Horizontal Pod Autoscaling](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-12-horizontal-pod-autoscaling)
- [Load Balancing](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-13-load-balancing)
- [Prometheus Metrics](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-14-prometheus-metrics)
- [Grafana Dashboards](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-15-grafana-dashboards)
- [CI/CD Pipeline](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-16-ci-cd-pipeline)
- [Canary Deployments](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-17-canary-deployments)
- [Rollback Strategies](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-18-rollback-strategies)
- [High Availability](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-19-high-availability)
- [Dockerfile Optimization](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-2-dockerfile-optimization)
- [Disaster Recovery](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-20-disaster-recovery)
- [Cost Optimization](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-21-cost-optimization)
- [Multi-Tenant Serving](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-22-multi-tenant-serving)
- [Security Hardening](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-23-security-hardening)
- [Production Stack Project](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-24-production-stack-project)
- [Multi-Stage Builds](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-3-multi-stage-builds)
- [Docker Compose for AI Stack](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-4-docker-compose-for-ai-stack)
- [GPU Access in Docker](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-5-gpu-access-in-docker)
- [Resource Limits](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-6-resource-limits)
- [Kubernetes Basics](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-7-kubernetes-basics)
- [GPU Node Selection](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-8-gpu-node-selection)
- [Kubernetes Deployments](https://www.runlocalai.co/learn/courses/production-ai-deployment/chapter-9-kubernetes-deployments)
- [The Fundamental Insight](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-1-the-fundamental-insight)
- [JSON Mode](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-10-json-mode)
- [Markdown Output](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-11-markdown-output)
- [Model-Specific Prompting: Llama](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-12-model-specific-prompting-llama)
- [Model-Specific: Qwen](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-13-model-specific-qwen)
- [Model-Specific: DeepSeek](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-14-model-specific-deepseek)
- [Tree-of-Thought](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-15-tree-of-thought)
- [Self-Consistency](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-16-self-consistency)
- [Prompt Chaining](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-17-prompt-chaining)
- [Template Libraries](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-18-template-libraries)
- [Prompt Evaluation](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-19-prompt-evaluation)
- [Prompt Anatomy](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-2-prompt-anatomy)
- [A/B Testing Prompts](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-20-a-b-testing-prompts)
- [Automated Optimization](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-21-automated-optimization)
- [Building a Prompt Kit](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-22-building-a-prompt-kit)
- [Cross-Model Testing](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-23-cross-model-testing)
- [Prompt Version Control](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-24-prompt-version-control)
- [Final Project: Prompt Framework](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-25-final-project-prompt-framework)
- [Zero-Shot Prompting](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-3-zero-shot-prompting)
- [Few-Shot Prompting](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-4-few-shot-prompting)
- [Chain-of-Thought](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-5-chain-of-thought)
- [Step-by-Step Reasoning](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-6-step-by-step-reasoning)
- [Role Prompting](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-7-role-prompting)
- [Personas for Different Tasks](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-8-personas-for-different-tasks)
- [Output Format Control](https://www.runlocalai.co/learn/courses/prompt-engineering/chapter-9-output-format-control)
- [Why Python for AI?](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-1-why-python-for-ai)
- [NumPy Arrays for ML](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-10-numpy-arrays-for-ml)
- [NumPy Operations](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-11-numpy-operations)
- [NumPy Broadcasting](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-12-numpy-broadcasting)
- [Pandas Series](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-13-pandas-series)
- [Pandas DataFrames](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-14-pandas-dataframes)
- [Data Cleaning with Pandas](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-15-data-cleaning-with-pandas)
- [Working with APIs](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-16-working-with-apis)
- [Rate Limiting and Retries](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-17-rate-limiting-and-retries)
- [Reading API Responses](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-18-reading-api-responses)
- [Object-Oriented Python](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-19-object-oriented-python)
- [Your Environment](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-2-your-environment)
- [Classes for AI Tools](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-20-classes-for-ai-tools)
- [Inheritance and Composition](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-21-inheritance-and-composition)
- [Regular Expressions](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-22-regular-expressions)
- [Text Processing with Regex](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-23-text-processing-with-regex)
- [Data Visualization with Matplotlib](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-24-data-visualization-with-matplotlib)
- [Plotting AI Metrics](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-25-plotting-ai-metrics)
- [Performance Profiling](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-26-performance-profiling)
- [Optimizing Python Code](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-27-optimizing-python-code)
- [Virtual Environments Deep Dive](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-28-virtual-environments-deep-dive)
- [Dependency Management](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-29-dependency-management)
- [Variables and Types](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-3-variables-and-types)
- [Project Structure for AI](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-30-project-structure-for-ai)
- [Building a CLI Tool](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-31-building-a-cli-tool)
- [CLI Argument Parsing](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-32-cli-argument-parsing)
- [CLI with Rich Output](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-33-cli-with-rich-output)
- [AI Pipeline Script](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-34-ai-pipeline-script)
- [Batch Processing with Progress](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-35-batch-processing-with-progress)
- [Final Project: AI Data Pipeline](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-36-final-project-ai-data-pipeline)
- [Control Flow](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-4-control-flow)
- [Functions](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-5-functions)
- [Lists and List Comprehensions](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-6-lists-and-list-comprehensions)
- [Dictionaries for AI Config](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-7-dictionaries-for-ai-config)
- [File I/O](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-8-file-i-o)
- [Error Handling](https://www.runlocalai.co/learn/courses/python-for-ai/chapter-9-error-handling)
- [Why Evaluate RAG?](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-1-why-evaluate-rag)
- [Hallucination Detection](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-10-hallucination-detection)
- [Evaluating with LLMs](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-11-evaluating-with-llms)
- [Building Test Datasets](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-12-building-test-datasets)
- [Synthetic Data Generation](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-13-synthetic-data-generation)
- [Human Annotation](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-14-human-annotation)
- [CI/CD for RAG](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-15-ci-cd-for-rag)
- [Regression Testing](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-16-regression-testing)
- [Monitoring RAG Quality](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-17-monitoring-rag-quality)
- [RAG Evaluation Dashboard Project](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-18-rag-evaluation-dashboard-project)
- [Retrieval Metrics: Hit Rate](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-2-retrieval-metrics-hit-rate)
- [Mean Reciprocal Rank](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-3-mean-reciprocal-rank)
- [NDCG Explained](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-4-ndcg-explained)
- [RAGAS Introduction](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-5-ragas-introduction)
- [Faithfulness](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-6-faithfulness)
- [Answer Relevance](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-7-answer-relevance)
- [Context Precision](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-8-context-precision)
- [Context Recall](https://www.runlocalai.co/learn/courses/rag-evaluation-metrics/chapter-9-context-recall)
- [What is RAG?](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-1-what-is-rag)
- [Embedding Pipeline](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-10-embedding-pipeline)
- [Storing Embeddings in ChromaDB](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-11-storing-embeddings-in-chromadb)
- [Retrieval Strategies](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-12-retrieval-strategies)
- [Dense Retrieval](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-13-dense-retrieval)
- [Sparse Retrieval (BM25)](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-14-sparse-retrieval-bm25)
- [Context Assembly](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-15-context-assembly)
- [Prompt with Retrieved Context](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-16-prompt-with-retrieved-context)
- [Basic Generation Pipeline](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-17-basic-generation-pipeline)
- [RAG Evaluation: Hit Rate](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-18-rag-evaluation-hit-rate)
- [RAG Evaluation: MRR](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-19-rag-evaluation-mrr)
- [RAG Architecture Overview](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-2-rag-architecture-overview)
- [Common RAG Failures](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-20-common-rag-failures)
- [RAG Pipeline Optimization](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-21-rag-pipeline-optimization)
- [Part 1 Final Project](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-22-part-1-final-project)
- [PDF Ingestion with PyMuPDF](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-3-pdf-ingestion-with-pymupdf)
- [HTML Ingestion](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-4-html-ingestion)
- [Markdown Ingestion](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-5-markdown-ingestion)
- [Fixed-Size Chunking](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-6-fixed-size-chunking)
- [Semantic Chunking](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-7-semantic-chunking)
- [Recursive Character Splitter](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-8-recursive-character-splitter)
- [Document Metadata Extraction](https://www.runlocalai.co/learn/courses/rag-systems-part-1/chapter-9-document-metadata-extraction)
- [Part 1 Recap](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-1-part-1-recap)
- [Adaptive Retrieval](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-10-adaptive-retrieval)
- [Agentic Retrieval](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-11-agentic-retrieval)
- [Multi-Hop RAG](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-12-multi-hop-rag)
- [Context Compression](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-13-context-compression)
- [Sliding Window Context](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-14-sliding-window-context)
- [Document Re-ranking](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-15-document-re-ranking)
- [Caching Strategies](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-16-caching-strategies)
- [Batch Processing](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-17-batch-processing)
- [Production Pipeline](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-18-production-pipeline)
- [Monitoring RAG Quality](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-19-monitoring-rag-quality)
- [Why Reranking Matters](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-2-why-reranking-matters)
- [A/B Testing Retrieval](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-20-a-b-testing-retrieval)
- [Advanced RAG Evaluation](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-21-advanced-rag-evaluation)
- [Part 2 Final Project](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-22-part-2-final-project)
- [Cross-Encoder Setup](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-3-cross-encoder-setup)
- [Local Cross-Encoder Models](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-4-local-cross-encoder-models)
- [Reranking Pipeline](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-5-reranking-pipeline)
- [Query Rewriting](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-6-query-rewriting)
- [Query Expansion](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-7-query-expansion)
- [Hybrid Search (Dense + Sparse)](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-8-hybrid-search-dense-sparse)
- [Reciprocal Rank Fusion](https://www.runlocalai.co/learn/courses/rag-systems-part-2/chapter-9-reciprocal-rank-fusion)
- [Why Alignment?](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-1-why-alignment)
- [PPO with KL Control](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-10-ppo-with-kl-control)
- [PPO Implementation](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-11-ppo-implementation)
- [Synthetic Preference Data](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-12-synthetic-preference-data)
- [Data Quality Filtering](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-13-data-quality-filtering)
- [Iterated Training](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-14-iterated-training)
- [Alignment Evaluation](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-15-alignment-evaluation)
- [Helpfulness vs Harmlessness](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-16-helpfulness-vs-harmlessness)
- [Constitutional AI](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-17-constitutional-ai)
- [RRHF and IPO](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-18-rrhf-and-ipo)
- [ORPO](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-19-orpo)
- [Preference Optimization Overview](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-2-preference-optimization-overview)
- [Multi-Turn Alignment](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-20-multi-turn-alignment)
- [Catastrophic Forgetting](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-21-catastrophic-forgetting)
- [Alignment on Consumer GPU](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-22-alignment-on-consumer-gpu)
- [Benchmarking Alignment](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-23-benchmarking-alignment)
- [Model Alignment Pipeline Project](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-24-model-alignment-pipeline-project)
- [DPO Theory](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-3-dpo-theory)
- [DPO Implementation with TRL](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-4-dpo-implementation-with-trl)
- [DPO Hyperparameters](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-5-dpo-hyperparameters)
- [Reward Model Training](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-6-reward-model-training)
- [Data Collection](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-7-data-collection)
- [Reward Model Evaluation](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-8-reward-model-evaluation)
- [PPO Theory](https://www.runlocalai.co/learn/courses/rlhf-dpo-ppo/chapter-9-ppo-theory)
- [AI in Scientific Research](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-1-ai-in-scientific-research)
- [Statistical Analysis Assistant](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-10-statistical-analysis-assistant)
- [Paper Writing Assistance](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-11-paper-writing-assistance)
- [Results Interpretation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-12-results-interpretation)
- [Peer Review Assistance](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-13-peer-review-assistance)
- [Review Response](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-14-review-response)
- [Research Documentation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-15-research-documentation)
- [Reproducibility](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-16-reproducibility)
- [Ethics in AI Research](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-17-ethics-in-ai-research)
- [Research Assistant Project](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-18-research-assistant-project)
- [Literature Automation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-2-literature-automation)
- [Paper Retrieval](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-3-paper-retrieval)
- [Citation Graph Analysis](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-4-citation-graph-analysis)
- [Summary Generation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-5-summary-generation)
- [Hypothesis Generation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-6-hypothesis-generation)
- [Literature Gap Analysis](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-7-literature-gap-analysis)
- [Experiment Design](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-8-experiment-design)
- [Protocol Generation](https://www.runlocalai.co/learn/courses/scientific-research-ai/chapter-9-protocol-generation)
- [Why Security Matters](https://www.runlocalai.co/learn/courses/security-privacy/chapter-1-why-security-matters)
- [Model Provenance](https://www.runlocalai.co/learn/courses/security-privacy/chapter-10-model-provenance)
- [Supply Chain Risks](https://www.runlocalai.co/learn/courses/security-privacy/chapter-11-supply-chain-risks)
- [GDPR Compliance](https://www.runlocalai.co/learn/courses/security-privacy/chapter-12-gdpr-compliance)
- [CCPA Considerations](https://www.runlocalai.co/learn/courses/security-privacy/chapter-13-ccpa-considerations)
- [Audit Logging](https://www.runlocalai.co/learn/courses/security-privacy/chapter-14-audit-logging)
- [Incident Response](https://www.runlocalai.co/learn/courses/security-privacy/chapter-15-incident-response)
- [Security Checklist Project](https://www.runlocalai.co/learn/courses/security-privacy/chapter-16-security-checklist-project)
- [Threat Modeling for AI](https://www.runlocalai.co/learn/courses/security-privacy/chapter-2-threat-modeling-for-ai)
- [Prompt Injection Attacks](https://www.runlocalai.co/learn/courses/security-privacy/chapter-3-prompt-injection-attacks)
- [API Authentication](https://www.runlocalai.co/learn/courses/security-privacy/chapter-4-api-authentication)
- [API Key Management](https://www.runlocalai.co/learn/courses/security-privacy/chapter-5-api-key-management)
- [Data Isolation](https://www.runlocalai.co/learn/courses/security-privacy/chapter-6-data-isolation)
- [Network Security](https://www.runlocalai.co/learn/courses/security-privacy/chapter-7-network-security)
- [Firewall Configuration](https://www.runlocalai.co/learn/courses/security-privacy/chapter-8-firewall-configuration)
- [HTTPS for Local APIs](https://www.runlocalai.co/learn/courses/security-privacy/chapter-9-https-for-local-apis)
- [Systematic Debugging Approach](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-1-systematic-debugging-approach)
- [Context Length Errors](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-10-context-length-errors)
- [Model Hallucination Debugging](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-11-model-hallucination-debugging)
- [Performance Profiling](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-12-performance-profiling)
- [Log Analysis](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-13-log-analysis)
- [Community Resources](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-14-community-resources)
- [Troubleshooting Runbook Project](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-15-troubleshooting-runbook-project)
- [Installation Failures](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-2-installation-failures)
- [GPU Not Detected](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-3-gpu-not-detected)
- [OOM Errors](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-4-oom-errors)
- [Model Download Failures](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-5-model-download-failures)
- [Slow Inference](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-6-slow-inference)
- [API Connection Refused](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-7-api-connection-refused)
- [Docker Issues](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-8-docker-issues)
- [WSL2 Problems](https://www.runlocalai.co/learn/courses/troubleshooting-local-ai/chapter-9-wsl2-problems)
- [What the Numbers Mean](https://www.runlocalai.co/learn/courses/understanding-models/chapter-1-what-the-numbers-mean)
- [GSM8K for Math](https://www.runlocalai.co/learn/courses/understanding-models/chapter-10-gsm8k-for-math)
- [Chatbot Arena Elo](https://www.runlocalai.co/learn/courses/understanding-models/chapter-11-chatbot-arena-elo)
- [Running Your Own Benchmarks](https://www.runlocalai.co/learn/courses/understanding-models/chapter-12-running-your-own-benchmarks)
- [Model Selection for Chat](https://www.runlocalai.co/learn/courses/understanding-models/chapter-13-model-selection-for-chat)
- [Model Selection for Code](https://www.runlocalai.co/learn/courses/understanding-models/chapter-14-model-selection-for-code)
- [Model Selection for Reasoning](https://www.runlocalai.co/learn/courses/understanding-models/chapter-15-model-selection-for-reasoning)
- [Instruct vs Base Models](https://www.runlocalai.co/learn/courses/understanding-models/chapter-16-instruct-vs-base-models)
- [Tokenizer Impact on Quality](https://www.runlocalai.co/learn/courses/understanding-models/chapter-17-tokenizer-impact-on-quality)
- [Emerging Model Families](https://www.runlocalai.co/learn/courses/understanding-models/chapter-18-emerging-model-families)
- [Open vs Closed Weights](https://www.runlocalai.co/learn/courses/understanding-models/chapter-19-open-vs-closed-weights)
- [Parameter Count Guide](https://www.runlocalai.co/learn/courses/understanding-models/chapter-2-parameter-count-guide)
- [Model Comparison Project](https://www.runlocalai.co/learn/courses/understanding-models/chapter-20-model-comparison-project)
- [Dense vs Mixture of Experts](https://www.runlocalai.co/learn/courses/understanding-models/chapter-3-dense-vs-mixture-of-experts)
- [Quantization Explained](https://www.runlocalai.co/learn/courses/understanding-models/chapter-4-quantization-explained)
- [Q4_K_M vs Q8_0 vs Q2_K](https://www.runlocalai.co/learn/courses/understanding-models/chapter-5-q4-k-m-vs-q8-0-vs-q2-k)
- [KV Cache and VRAM](https://www.runlocalai.co/learn/courses/understanding-models/chapter-6-kv-cache-and-vram)
- [Context Length Tradeoffs](https://www.runlocalai.co/learn/courses/understanding-models/chapter-7-context-length-tradeoffs)
- [MMLU Benchmark Explained](https://www.runlocalai.co/learn/courses/understanding-models/chapter-8-mmlu-benchmark-explained)
- [HumanEval for Code](https://www.runlocalai.co/learn/courses/understanding-models/chapter-9-humaneval-for-code)
- [Why Build a Vector DB?](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-1-why-build-a-vector-db)
- [HNSW Parameters](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-10-hnsw-parameters)
- [Product Quantization](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-11-product-quantization)
- [PQ Encoding and Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-12-pq-encoding-and-search)
- [SIMD Distance Computation](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-13-simd-distance-computation)
- [Multi-Tier Indexing](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-14-multi-tier-indexing)
- [Distributed Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-15-distributed-search)
- [Index Persistence](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-16-index-persistence)
- [Filtering and Hybrid Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-17-filtering-and-hybrid-search)
- [Minimal Vector Database Project](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-18-minimal-vector-database-project)
- [Vector Search Fundamentals](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-2-vector-search-fundamentals)
- [Brute Force Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-3-brute-force-search)
- [IVF: Inverted File Index](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-4-ivf-inverted-file-index)
- [IVF Training and Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-5-ivf-training-and-search)
- [IVF Parameters](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-6-ivf-parameters)
- [HNSW: Hierarchical Navigable Small World](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-7-hnsw-hierarchical-navigable-small-world)
- [HNSW Construction](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-8-hnsw-construction)
- [HNSW Search](https://www.runlocalai.co/learn/courses/vector-database-internals/chapter-9-hnsw-search)
- [What is an Embedding?](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-1-what-is-an-embedding)
- [IVF vs HNSW](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-10-ivf-vs-hnsw)
- [FAISS with LangChain](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-11-faiss-with-langchain)
- [Semantic Search Engine](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-12-semantic-search-engine)
- [Indexing Strategies](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-13-indexing-strategies)
- [Batch Ingestion](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-14-batch-ingestion)
- [Embedding Caching](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-15-embedding-caching)
- [Performance Optimization](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-16-performance-optimization)
- [ChromaDB Persistence](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-17-chromadb-persistence)
- [Search Engine Project](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-18-search-engine-project)
- [Embedding Models Compared](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-2-embedding-models-compared)
- [ChromaDB Setup](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-3-chromadb-setup)
- [ChromaDB Collections](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-4-chromadb-collections)
- [Adding Documents](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-5-adding-documents)
- [Similarity Search](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-6-similarity-search)
- [Metadata Filtering](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-7-metadata-filtering)
- [FAISS Installation](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-8-faiss-installation)
- [FAISS Index Types](https://www.runlocalai.co/learn/courses/vector-stores-embeddings/chapter-9-faiss-index-types)
- [Voice AI Overview](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-1-voice-ai-overview)
- [Real-Time Architecture](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-10-real-time-architecture)
- [WebSocket Server](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-11-websocket-server)
- [WebSocket Client](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-12-websocket-client)
- [Multi-Language Support](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-13-multi-language-support)
- [Noise Reduction](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-14-noise-reduction)
- [Voice Cloning](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-15-voice-cloning)
- [Low-Latency Optimization](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-16-low-latency-optimization)
- [Model Quantization for Voice](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-17-model-quantization-for-voice)
- [Error Handling](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-18-error-handling)
- [Testing Voice Pipelines](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-19-testing-voice-pipelines)
- [Whisper Installation](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-2-whisper-installation)
- [Docker Deployment](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-20-docker-deployment)
- [Performance Benchmarks](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-21-performance-benchmarks)
- [Voice Assistant Project](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-22-voice-assistant-project)
- [Whisper Model Selection](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-3-whisper-model-selection)
- [STT Accuracy Tuning](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-4-stt-accuracy-tuning)
- [Voice Activity Detection](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-5-voice-activity-detection)
- [TTS Options: Kokoro](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-6-tts-options-kokoro)
- [TTS: XTTS-v2](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-7-tts-xtts-v2)
- [TTS: Piper](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-8-tts-piper)
- [STT→LLM→TTS Pipeline](https://www.runlocalai.co/learn/courses/voice-ai-local/chapter-9-stt-llm-tts-pipeline)
- [AI is Not Magic](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-1-ai-is-not-magic)
- [Interface Options](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-10-interface-options)
- [Understanding Model Responses](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-11-understanding-model-responses)
- [System Prompts](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-12-system-prompts)
- [Temperature and Sampling](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-13-temperature-and-sampling)
- [Context Windows](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-14-context-windows)
- [Common Use Cases](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-15-common-use-cases)
- [When NOT to Use Local AI](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-16-when-not-to-use-local-ai)
- [Community and Ecosystem](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-17-community-and-ecosystem)
- [Your Recommended Path](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-18-your-recommended-path)
- [Project - First Week with Local AI](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-19-project-first-week-with-local-ai)
- [The Two Worlds - Cloud vs Local](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-2-the-two-worlds-cloud-vs-local)
- [Project - Local vs Cloud Cost Analysis](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-20-project-local-vs-cloud-cost-analysis)
- [What Can You Actually Run Locally?](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-3-what-can-you-actually-run-locally)
- [What is a Model, Really?](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-4-what-is-a-model-really)
- [The Economics](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-5-the-economics)
- [Privacy - What Stays Yours](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-6-privacy-what-stays-yours)
- [Hardware Minimums](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-7-hardware-minimums)
- [Installing Your First Local AI](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-8-installing-your-first-local-ai)
- [Your First Conversation](https://www.runlocalai.co/learn/courses/what-is-local-ai/chapter-9-your-first-conversation)

## Glossary (440)
- [A/B Testing](https://www.runlocalai.co/glossary/ab-testing): A/B Testing in ML compares two model variants — a control (current production model) and a treatment (candidate model) — by randomly splitt…
- [Accountability (AI)](https://www.runlocalai.co/glossary/accountability): Accountability in AI means that the operator or organization deploying a model can be held responsible for its outputs and behavior. For lo…
- [Accuracy](https://www.runlocalai.co/glossary/accuracy): Accuracy measures how often a model's predictions match the expected ground truth, typically expressed as a percentage (e.g., 95% means 95…
- [Adam Optimizer](https://www.runlocalai.co/glossary/adam): Adam (Adaptive Moment Estimation) is an optimizer that adjusts learning rates per parameter during training. It combines momentum (moving a…
- [AdamW](https://www.runlocalai.co/glossary/adamw): AdamW is an optimizer algorithm used during fine-tuning or training of neural networks, including LLMs. It modifies the standard Adam optim…
- [Adversarial Attack](https://www.runlocalai.co/glossary/adversarial-attack): An adversarial attack is a technique where small, often imperceptible perturbations are added to an input to cause a machine learning model…
- [Adversarial Example](https://www.runlocalai.co/glossary/adversarial-example): An adversarial example is an input to a machine learning model that has been intentionally perturbed to cause a misprediction, while appear…
- [Agent Memory (Short/Long/Episodic)](https://www.runlocalai.co/glossary/agent-memory): Agent memory refers to the mechanisms an AI agent uses to store and recall information across interactions. Short-term memory holds context…
- [Artificial General Intelligence (AGI)](https://www.runlocalai.co/glossary/agi): Artificial General Intelligence (AGI) refers to a hypothetical AI system that can perform any intellectual task that a human can, across a…
- [AI Agent](https://www.runlocalai.co/glossary/ai-agent): An AI agent is software that uses an LLM to decide what to do, takes actions, observes results, and iterates toward a goal. Unlike a chatbo…
- [AI Alignment](https://www.runlocalai.co/glossary/ai-alignment): AI alignment refers to the challenge of ensuring that a model's outputs match the operator's intended goals and values. In practice, an una…
- [AI Ethics](https://www.runlocalai.co/glossary/ai-ethics): AI ethics refers to the principles and practices that guide the responsible development and deployment of AI systems. For operators running…
- [AI in Finance](https://www.runlocalai.co/glossary/ai-finance): AI in Finance refers to the application of machine learning and deep learning models to financial tasks like fraud detection, algorithmic t…
- [AI Governance](https://www.runlocalai.co/glossary/ai-governance): AI Governance refers to the set of policies, processes, and technical controls that determine how a model is developed, deployed, monitored…
- [AI Regulation](https://www.runlocalai.co/glossary/ai-regulation): AI regulation refers to laws, policies, and guidelines that govern the development, deployment, and use of AI systems. For operators runnin…
- [AI Safety](https://www.runlocalai.co/glossary/ai-safety): AI safety refers to the set of practices and research aimed at ensuring that AI systems behave reliably, predictably, and in alignment with…
- [Airflow](https://www.runlocalai.co/glossary/airflow): Airflow is a workflow orchestration tool for scheduling, monitoring, and managing complex data pipelines as directed acyclic graphs (DAGs).…
- [Algorithmic Bias](https://www.runlocalai.co/glossary/algorithmic-bias): Algorithmic bias refers to systematic and repeatable errors in a model's outputs that create unfair outcomes, such as privileging one group…
- [Algorithmic Trading](https://www.runlocalai.co/glossary/algorithmic-trading): Algorithmic trading uses computer programs to execute financial trades based on predefined rules, often involving statistical models and re…
- [ALiBi (Attention with Linear Biases)](https://www.runlocalai.co/glossary/alibi): ALiBi is a positional encoding scheme that biases attention scores by a linear function of token distance, instead of injecting position in…
- [Alignment](https://www.runlocalai.co/glossary/alignment): Alignment refers to the process of fine-tuning a base LLM so its outputs match human preferences, values, or safety guidelines. Operators e…
- [AlphaFold](https://www.runlocalai.co/glossary/alphafold): AlphaFold is a deep learning model developed by DeepMind that predicts the 3D structure of proteins from their amino acid sequence. For ope…
- [AlphaGo](https://www.runlocalai.co/glossary/alphago): AlphaGo is a computer program developed by DeepMind that plays the board game Go at a superhuman level. It combines deep neural networks wi…
- [AlphaZero](https://www.runlocalai.co/glossary/alphazero): AlphaZero is a reinforcement learning algorithm developed by DeepMind that learns to master board games (Go, chess, shogi) from scratch, wi…
- [Annotation](https://www.runlocalai.co/glossary/annotation): Annotation is the process of adding labels, tags, or metadata to raw data (text, images, audio) to create a training dataset for supervised…
- [Anomaly Detection](https://www.runlocalai.co/glossary/anomaly-detection): Anomaly detection is the task of identifying data points, events, or patterns that deviate significantly from a dataset's norm. In local AI…
- [Anthropic](https://www.runlocalai.co/glossary/anthropic): Anthropic is an AI safety and research company that develops large language models (LLMs) under the Claude family. Operators encounter Anth…
- [Artificial Intelligence (AI)](https://www.runlocalai.co/glossary/artificial-intelligence): Artificial Intelligence (AI) refers to systems that perform tasks typically requiring human intelligence, such as reasoning, learning, and…
- [Artificial Superintelligence (ASI)](https://www.runlocalai.co/glossary/asi): Artificial Superintelligence (ASI) refers to a hypothetical AI system that surpasses human intelligence across all domains—creativity, prob…
- [Automatic Speech Recognition (ASR)](https://www.runlocalai.co/glossary/asr): Automatic Speech Recognition (ASR) converts spoken audio into text. Operators encounter ASR when running models like Whisper locally to tra…
- [Attention Mechanism](https://www.runlocalai.co/glossary/attention): The attention mechanism is a neural network component that lets a model weigh the importance of different parts of the input when producing…
- [AUC (Area Under Curve)](https://www.runlocalai.co/glossary/auc): AUC (Area Under the Curve) measures a model's ability to rank positive examples higher than negative ones, typically using the ROC curve (T…
- [Audio Generation](https://www.runlocalai.co/glossary/audio-generation): Audio generation refers to the process of creating audio content—such as speech, music, or sound effects—using machine learning models. In…
- [Autoencoder](https://www.runlocalai.co/glossary/autoencoder): An autoencoder is a neural network trained to reconstruct its input after passing it through a bottleneck layer. The bottleneck forces the…
- [Autonomous Agent](https://www.runlocalai.co/glossary/autonomous-agent): An autonomous agent is a system that uses a language model to decide and execute multi-step tasks without human intervention at each step.…
- [Autonomous Vehicles](https://www.runlocalai.co/glossary/autonomous-vehicles): Autonomous vehicles are self-driving systems that use AI to perceive their environment, plan routes, and control vehicle motion without hum…
- [Autoregressive Models](https://www.runlocalai.co/glossary/autoregressive-models): Autoregressive models generate text one token at a time, where each new token depends on all previously generated tokens. In practice, this…
- [AWQ](https://www.runlocalai.co/glossary/awq): AWQ (Activation-aware Weight Quantization) is a 4-bit quantization method designed for fast inference on NVIDIA GPUs. It's the production-d…
- [Backpropagation](https://www.runlocalai.co/glossary/backpropagation): Backpropagation is the algorithm used to train neural networks by computing gradients of the loss function with respect to each weight. It…
- [Batch Normalization](https://www.runlocalai.co/glossary/batch-normalization): Batch normalization is a training technique that normalizes the inputs to a layer across a mini-batch of data. It computes the mean and var…
- [Batch Size](https://www.runlocalai.co/glossary/batch-size): Batch size is the number of training samples processed together in one forward and backward pass. In local AI training, it directly determi…
- [BERT](https://www.runlocalai.co/glossary/bert): BERT (Bidirectional Encoder Representations from Transformers) is a transformer-based language model that reads text in both directions sim…
- [BF16 (BFloat16)](https://www.runlocalai.co/glossary/bf16): BF16 (Brain Floating Point 16) is a 16-bit floating-point number format that uses 8 exponent bits and 7 mantissa bits, matching the dynamic…
- [Bias (AI/ML)](https://www.runlocalai.co/glossary/bias): Bias in AI/ML refers to systematic errors in model outputs that result from skewed training data, flawed assumptions, or algorithmic design…
- [Bias-Variance Tradeoff](https://www.runlocalai.co/glossary/bias-variance): The bias-variance tradeoff describes the tension between a model's ability to fit training data closely (low bias) and its sensitivity to v…
- [BLEU score](https://www.runlocalai.co/glossary/bleu): BLEU (Bilingual Evaluation Understudy) is an automated metric that measures how similar a machine-generated text is to one or more human-wr…
- [BM25 (Best Matching 25)](https://www.runlocalai.co/glossary/bm25): BM25 is the canonical sparse-retrieval algorithm: a TF-IDF variant that saturates term frequency (a token appearing 100 times isn't 100× mo…
- [Byte Pair Encoding (BPE)](https://www.runlocalai.co/glossary/bpe): Byte Pair Encoding (BPE) is a subword tokenization algorithm that splits text into a sequence of tokens by iteratively merging the most fre…
- [Browser Agent](https://www.runlocalai.co/glossary/browser-agent): A browser agent is an AI-driven program that controls a web browser to automate tasks like form filling, data extraction, or navigation. It…
- [CatBoost](https://www.runlocalai.co/glossary/catboost): CatBoost is a gradient boosting library developed by Yandex that handles categorical features automatically without manual encoding. For op…
- [Chain-of-Thought (CoT)](https://www.runlocalai.co/glossary/chain-of-thought): Chain-of-thought prompting is asking a model to show its reasoning step-by-step before giving the final answer. It dramatically improves ac…
- [Chunked Prefill](https://www.runlocalai.co/glossary/chunked-prefill): Chunked prefill is an inference-engine technique that splits long-prompt processing into smaller chunks so the engine can interleave decode…
- [CIFAR-10/100](https://www.runlocalai.co/glossary/cifar): CIFAR-10 and CIFAR-100 are datasets of 32x32 color images used for benchmarking image classification models. CIFAR-10 has 10 classes (e.g.,…
- [Claude (Anthropic)](https://www.runlocalai.co/glossary/claude): Claude is a family of large language models (LLMs) developed by Anthropic, designed for safe and helpful text generation. Operators encount…
- [Convolutional Neural Network (CNN)](https://www.runlocalai.co/glossary/cnn): A Convolutional Neural Network (CNN) is a neural network architecture that uses convolutional layers to process grid-like data, such as ima…
- [COCO](https://www.runlocalai.co/glossary/coco): COCO (Common Objects in Context) is a large-scale image dataset created by Microsoft for object detection, segmentation, and captioning. It…
- [Coding Agent](https://www.runlocalai.co/glossary/coding-agent): A coding agent is a language model configured to write, debug, or refactor code autonomously or semi-autonomously. It typically runs in a l…
- [Computer Vision (domain)](https://www.runlocalai.co/glossary/computer-vision-domain): Computer vision is the field of AI that enables machines to interpret and process visual data—images, videos, or live camera feeds—by assig…
- [Concept Drift](https://www.runlocalai.co/glossary/concept-drift): Concept drift is a change in the statistical properties of a target variable over time, causing a trained model to become less accurate. In…
- [Confusion Matrix](https://www.runlocalai.co/glossary/confusion-matrix): A confusion matrix is a table that summarizes the performance of a classification model by comparing predicted labels against actual labels…
- [Constitutional AI](https://www.runlocalai.co/glossary/constitutional-ai): Constitutional AI (CAI) is a training method that aligns language model behavior using a set of written rules (a 'constitution') rather tha…
- [Context Window](https://www.runlocalai.co/glossary/context-window): The context window is the maximum number of tokens a model can attend to at once — both prompt and previously generated tokens. Llama 3.1 8…
- [Continual Learning](https://www.runlocalai.co/glossary/continual-learning): Continual learning (also called lifelong learning) is a machine learning paradigm where a model is trained on a sequence of tasks without f…
- [Continuous Batching](https://www.runlocalai.co/glossary/continuous-batching): Continuous batching (sometimes "iteration-level scheduling") is a serving optimization where new requests join the active batch as soon as…
- [Contrastive Learning](https://www.runlocalai.co/glossary/contrastive-learning): Contrastive learning is a self-supervised training method where a model learns to pull similar data points (e.g., two augmented views of th…
- [ControlNet](https://www.runlocalai.co/glossary/controlnet): ControlNet is a neural network architecture that adds spatial conditioning to pretrained image diffusion models (like Stable Diffusion). It…
- [CPU Offload](https://www.runlocalai.co/glossary/cpu-offload): CPU offload is a technique where parts of a neural network model are processed by the CPU instead of the GPU, typically because the model e…
- [Cross-Attention](https://www.runlocalai.co/glossary/cross-attention): Cross-attention is a mechanism in transformer models where the query vectors come from one sequence (e.g., the decoder's current output) an…
- [Cross-Validation](https://www.runlocalai.co/glossary/cross-validation): Cross-validation is a technique for evaluating how well a model generalizes to unseen data by partitioning the dataset into multiple folds,…
- [CUDA](https://www.runlocalai.co/glossary/cuda): CUDA (Compute Unified Device Architecture) is NVIDIA's parallel-computing platform and the dominant API for GPU-accelerated AI. Every major…
- [cuDNN](https://www.runlocalai.co/glossary/cudnn): cuDNN (CUDA Deep Neural Network library) is NVIDIA's GPU-accelerated library for deep learning primitives like convolutions, pooling, norma…
- [DALL-E](https://www.runlocalai.co/glossary/dalle): DALL-E is a family of text-to-image generative models developed by OpenAI. Operators encounter it as a cloud-only API service — unlike Stab…
- [Data Augmentation](https://www.runlocalai.co/glossary/data-augmentation): Data augmentation is the technique of generating modified copies of existing training data to increase dataset size and diversity without c…
- [Data Labeling](https://www.runlocalai.co/glossary/data-labeling): Data labeling is the process of annotating raw data (text, images, audio) with tags or categories that teach a model what to predict. In lo…
- [Data Parallelism](https://www.runlocalai.co/glossary/data-parallelism): Data parallelism is a distributed training strategy where a model is replicated across multiple devices (GPUs or nodes), and each replica p…
- [Data Pipeline](https://www.runlocalai.co/glossary/data-pipeline): A data pipeline is a sequence of automated steps that ingest, transform, and load data from source to destination. In local AI, operators b…
- [DBSCAN](https://www.runlocalai.co/glossary/dbscan): DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is an unsupervised clustering algorithm that groups data points based…
- [DDPM (Denoising Diffusion Probabilistic Models)](https://www.runlocalai.co/glossary/ddpm): DDPM (Denoising Diffusion Probabilistic Models) is a class of generative models that learn to generate data by reversing a gradual noising…
- [Decision Tree](https://www.runlocalai.co/glossary/decision-tree): A decision tree is a supervised learning model that splits data into branches based on feature values, forming a tree-like structure of dec…
- [Decode (Token Generation)](https://www.runlocalai.co/glossary/decode-phase): Decode is the second phase of LLM inference: generating one output token at a time, autoregressively. Each decode step does a small matrix-…
- [Decoder](https://www.runlocalai.co/glossary/decoder): A decoder is the component of a transformer model that generates output tokens one at a time, using the input's encoded representation and…
- [Decoder-Only Transformer](https://www.runlocalai.co/glossary/decoder-only): Decoder-only is the architecture of GPT, Llama, Qwen, Mistral, DeepSeek, and almost every modern open-weight LLM. The model is a stack of t…
- [Deep Learning (DL)](https://www.runlocalai.co/glossary/deep-learning): Deep learning (DL) is a subset of machine learning that uses multi-layer neural networks to learn patterns from data. In local AI, operator…
- [Deep Reinforcement Learning](https://www.runlocalai.co/glossary/deep-rl): Deep Reinforcement Learning (DRL) combines deep neural networks with reinforcement learning, enabling agents to learn optimal actions throu…
- [Deepfake](https://www.runlocalai.co/glossary/deepfake): A deepfake is a synthetic media (image, video, or audio) generated or manipulated by a deep learning model, typically an autoencoder or GAN…
- [DeepSeek](https://www.runlocalai.co/glossary/deepseek-family): DeepSeek is a family of open-weight large language models developed by DeepSeek (深度求索), a Chinese AI research company. The models range fro…
- [DeepSpeed](https://www.runlocalai.co/glossary/deepspeed): DeepSpeed is a deep learning optimization library by Microsoft that reduces memory usage and speeds up training for large models. It introd…
- [Dense Model](https://www.runlocalai.co/glossary/dense-model): A dense model activates every parameter on every forward pass — the default architecture for transformers like Llama, Qwen, and Mistral 7B.…
- [Dense Retrieval](https://www.runlocalai.co/glossary/dense-retrieval): Dense retrieval finds documents by computing cosine similarity (or dot product) between learned vector embeddings of the query and each doc…
- [Depth Estimation](https://www.runlocalai.co/glossary/depth-estimation): Depth estimation is a computer vision task that predicts a depth value for each pixel in an image, producing a depth map where closer objec…
- [Deterministic Decoding](https://www.runlocalai.co/glossary/deterministic-decoding): Deterministic decoding means same prompt → same output, every time. Achieved by setting temperature to 0 (always pick the highest-probabili…
- [Differential Privacy](https://www.runlocalai.co/glossary/differential-privacy): Differential Privacy is a mathematical framework that provides a formal guarantee that the output of an analysis reveals almost nothing abo…
- [Diffusion Model](https://www.runlocalai.co/glossary/diffusion-model): A diffusion model is a type of generative model that learns to reverse a gradual noising process. During training, the model learns to pred…
- [DirectML](https://www.runlocalai.co/glossary/directml): DirectML is Microsoft's GPU-agnostic ML acceleration API, layered on DirectX 12. It works on any Windows-supported GPU — NVIDIA, AMD, Intel…
- [Distillation](https://www.runlocalai.co/glossary/distillation): Distillation is a training technique where a smaller 'student' model learns to mimic the behavior of a larger 'teacher' model. The student…
- [Distributed Training](https://www.runlocalai.co/glossary/distributed-training): Distributed training splits the work of training a neural network across multiple GPUs or machines, using techniques like data parallelism…
- [DoRA (Weight-Decomposed Low-Rank Adaptation)](https://www.runlocalai.co/glossary/dora): DoRA (Weight-Decomposed Low-Rank Adaptation) is a fine-tuning method that improves upon LoRA by decomposing pre-trained weights into magnit…
- [Direct Preference Optimization (DPO)](https://www.runlocalai.co/glossary/dpo): Direct Preference Optimization (DPO) is a method for fine-tuning language models to align with human preferences without using reinforcemen…
- [DreamBooth](https://www.runlocalai.co/glossary/dreambooth): DreamBooth is a fine-tuning technique that personalizes a text-to-image model (like Stable Diffusion) to generate images of a specific subj…
- [Dropout](https://www.runlocalai.co/glossary/dropout): Dropout is a regularization technique used during neural network training where randomly selected neurons are ignored (dropped out) with a…
- [Drug Discovery (AI)](https://www.runlocalai.co/glossary/drug-discovery): Drug discovery with AI applies machine learning to the process of identifying and designing new pharmaceutical compounds. Operators encount…
- [Early Stopping](https://www.runlocalai.co/glossary/early-stopping): Early stopping is a training technique that halts model training when performance on a validation set stops improving, preventing overfitti…
- [Edge AI](https://www.runlocalai.co/glossary/edge-ai): Edge AI refers to running machine learning models locally on consumer hardware (laptops, phones, GPUs) rather than sending data to a cloud…
- [Edge Computing](https://www.runlocalai.co/glossary/edge-computing): Edge computing means running AI inference on a local device (laptop, phone, embedded system) instead of sending data to a remote cloud serv…
- [Edge Detection](https://www.runlocalai.co/glossary/edge-detection): Edge detection is a computer vision technique that identifies points in an image where brightness changes sharply, forming boundaries of ob…
- [Elo Rating (LLM benchmarks)](https://www.runlocalai.co/glossary/elo-rating): Elo rating in LLM benchmarks is a relative scoring system that ranks models based on pairwise comparison results, typically from human or a…
- [Embedding (Vector Embedding)](https://www.runlocalai.co/glossary/embedding): An embedding is a fixed-length vector representation of text, image, or other input — typically 384-3072 dimensions — where semantic simila…
- [Embodied AI](https://www.runlocalai.co/glossary/embodied-ai): Embodied AI refers to AI systems that interact with the physical world through a body or sensorimotor capabilities, rather than operating p…
- [Encoder](https://www.runlocalai.co/glossary/encoder): An encoder is a neural network component that processes input data (text, images, audio) into a dense representation—a vector or sequence o…
- [Encoder-Decoder](https://www.runlocalai.co/glossary/encoder-decoder): An encoder-decoder is a neural network architecture that processes an input sequence through an encoder to produce a compressed representat…
- [Encoder-Decoder Transformer](https://www.runlocalai.co/glossary/encoder-decoder-arch): Encoder-decoder transformers (T5, BART, original "Attention is All You Need" architecture) have two halves: an encoder reads the input bidi…
- [Epoch](https://www.runlocalai.co/glossary/epoch): An epoch is one complete pass through the entire training dataset during model training. In practice, operators fine-tuning a model (e.g.,…
- [ETL](https://www.runlocalai.co/glossary/etl): ETL (Extract, Transform, Load) is a data pipeline process that pulls raw data from sources (Extract), cleans or reformats it (Transform), a…
- [EU AI Act](https://www.runlocalai.co/glossary/eu-ai-act): The EU AI Act is a regulatory framework from the European Union that classifies AI systems by risk level (unacceptable, high, limited, mini…
- [EXL2](https://www.runlocalai.co/glossary/exl2): EXL2 is the ExLlamaV2 quantization format. NVIDIA-only, single-stream-throughput-optimized. Allows fractional bit-rates (e.g. 4.65 bits per…
- [ExLlamaV2](https://www.runlocalai.co/glossary/exllamav2): ExLlamaV2 is a high-performance inference engine for Llama-family models, optimized for GPU execution. It achieves faster token generation…
- [Expert Parallelism](https://www.runlocalai.co/glossary/expert-parallelism): Expert parallelism is a parallelism strategy specific to MoE models: each GPU holds a different subset of the experts, and tokens are route…
- [Explainability](https://www.runlocalai.co/glossary/explainability): Explainability refers to the ability to understand and interpret why a model produces a specific output. For local AI operators, this matte…
- [Exploding Gradient](https://www.runlocalai.co/glossary/exploding-gradient): An exploding gradient occurs when the gradients used to update model weights during training grow exponentially large, causing unstable upd…
- [F1 Score](https://www.runlocalai.co/glossary/f1-score): The F1 score is the harmonic mean of precision and recall, giving a single metric that balances false positives and false negatives. It ran…
- [Face Recognition](https://www.runlocalai.co/glossary/face-recognition): Face recognition is a computer vision task that identifies or verifies a person from an image or video frame by comparing facial features a…
- [Fairness (in AI)](https://www.runlocalai.co/glossary/fairness): Fairness in AI refers to the absence of systematic bias in model outputs across different demographic groups. For operators running local m…
- [FAISS](https://www.runlocalai.co/glossary/faiss): FAISS (Facebook AI Similarity Search) is a C++/Python library for fast approximate nearest-neighbor search over dense vectors. The de-facto…
- [FastText](https://www.runlocalai.co/glossary/fasttext): FastText is a library for efficient learning of word representations and sentence classification, developed by Facebook AI Research. It rep…
- [Feature Engineering](https://www.runlocalai.co/glossary/feature-engineering): Feature engineering is the process of transforming raw data into input variables (features) that improve model performance. In local AI, th…
- [Feature Extraction](https://www.runlocalai.co/glossary/feature-extraction): Feature extraction is the process of converting raw input data (like an image) into a compact set of numerical representations, or features…
- [Feature Scaling](https://www.runlocalai.co/glossary/feature-scaling): Feature scaling adjusts the range of numeric input values so that each feature contributes equally to a model's training. In practice, oper…
- [Feature Selection](https://www.runlocalai.co/glossary/feature-selection): Feature selection is the process of identifying and retaining only the most relevant input variables (features) for a machine learning mode…
- [Federated Learning](https://www.runlocalai.co/glossary/federated-learning): Federated learning is a machine learning technique where a model is trained across multiple decentralized devices or servers holding local…
- [Feedforward Neural Network](https://www.runlocalai.co/glossary/feedforward-nn): A feedforward neural network (FFNN) is the simplest type of neural network where connections between nodes do not form cycles. Data moves i…
- [Few-Shot Learning](https://www.runlocalai.co/glossary/few-shot-learning): Few-shot learning is a technique where a model performs a task after seeing only a small number of examples (typically 2–5) in the prompt,…
- [Few-Shot Prompting](https://www.runlocalai.co/glossary/few-shot-prompting): Few-shot prompting is a technique where you include a small number of input-output examples in the prompt to guide the model's response, wi…
- [FID (Fréchet Inception Distance)](https://www.runlocalai.co/glossary/fid): FID (Fréchet Inception Distance) is a metric that measures the quality of images generated by a model by comparing the statistical distribu…
- [Fine-tuning](https://www.runlocalai.co/glossary/fine-tuning): Fine-tuning is continued training of a pre-trained model on a smaller, task-specific dataset. Pre-training builds general capability from t…
- [Flash Attention](https://www.runlocalai.co/glossary/flash-attention): Flash Attention is a memory-efficient implementation of the attention mechanism that reduces memory usage from O(n²) to O(n) for sequence l…
- [FLOPS](https://www.runlocalai.co/glossary/flops): FLOPS (Floating Point Operations Per Second) measures how many floating-point calculations a processor can perform in one second. In local…
- [Foundation Model](https://www.runlocalai.co/glossary/foundation-model): A foundation model is a large neural network trained on broad data at scale, designed to be adapted for a wide range of downstream tasks ra…
- [FP16](https://www.runlocalai.co/glossary/fp16): FP16 (16-bit floating point) is a number format that uses 16 bits per weight or activation, balancing precision and memory. In local AI, FP…
- [FP32](https://www.runlocalai.co/glossary/fp32): FP32 (32-bit floating point) is a numerical format that uses 32 bits to represent each model weight, offering high precision at the cost of…
- [FP8](https://www.runlocalai.co/glossary/fp8): FP8 (Floating Point 8) is an 8-bit floating-point number format used in AI inference and training to reduce memory and computation requirem…
- [Fraud Detection](https://www.runlocalai.co/glossary/fraud-detection): Fraud detection is a machine learning task that identifies suspicious transactions, account activities, or user behaviors in real time. Ope…
- [FSDP (Fully Sharded Data Parallel)](https://www.runlocalai.co/glossary/fsdp): FSDP (Fully Sharded Data Parallel) is a distributed training technique that shards model parameters, gradients, and optimizer states across…
- [Function Calling / Tool Use](https://www.runlocalai.co/glossary/function-calling): Function calling (also called tool use) is a capability where the model emits structured JSON requesting that specific tools be called with…
- [Game AI](https://www.runlocalai.co/glossary/game-ai): Game AI refers to the algorithms and systems that control non-player characters (NPCs), opponents, and procedural content in video games. U…
- [Generative Adversarial Network (GAN)](https://www.runlocalai.co/glossary/gan): A Generative Adversarial Network (GAN) is a machine learning architecture where two neural networks—a generator and a discriminator—compete…
- [GDDR7](https://www.runlocalai.co/glossary/gddr7): GDDR7 uses PAM3 signaling to push per-pin rates to 28–32 Gbps in first-gen products (2025), with a path to 40+ Gbps. RTX 50 series adopts i…
- [Gemini (Google)](https://www.runlocalai.co/glossary/gemini): Gemini is a family of multimodal large language models (LLMs) developed by Google DeepMind, designed to process text, images, audio, video,…
- [Generative AI (GenAI)](https://www.runlocalai.co/glossary/genai): Generative AI (GenAI) refers to machine learning models that produce new content—text, images, audio, code, or video—by learning patterns f…
- [Generative Model](https://www.runlocalai.co/glossary/generative-model): A generative model is a type of machine learning model that learns the underlying distribution of training data and can then produce new sa…
- [GGML](https://www.runlocalai.co/glossary/ggml): GGML is the C/C++ tensor library that underlies llama.cpp, whisper.cpp, and the original GGUF format. It provides quantized integer kernels…
- [GGUF](https://www.runlocalai.co/glossary/gguf): GGUF (GGML Unified Format) is the file format used by llama.cpp and its ecosystem (Ollama, KoboldCPP, LM Studio). A single file contains th…
- [GloVe](https://www.runlocalai.co/glossary/glove): GloVe (Global Vectors for Word Representation) is a static word embedding method that learns vector representations of words by factorizing…
- [GLUE benchmark](https://www.runlocalai.co/glossary/glue): The GLUE (General Language Understanding Evaluation) benchmark is a collection of nine natural language understanding tasks, such as sentim…
- [Graph Neural Network (GNN)](https://www.runlocalai.co/glossary/gnn): A Graph Neural Network (GNN) is a neural network architecture designed to process data structured as graphs—nodes connected by edges. Unlik…
- [Google DeepMind](https://www.runlocalai.co/glossary/google-deepmind): Google DeepMind is an AI research lab formed from the 2023 merger of Google Brain and DeepMind. It develops large language models (e.g., Ge…
- [GPT-4](https://www.runlocalai.co/glossary/gpt-4): GPT-4 is a large multimodal language model developed by OpenAI, released in March 2023. It accepts text and image inputs and produces text…
- [GPT-5](https://www.runlocalai.co/glossary/gpt-5): GPT-5 is the hypothetical successor to OpenAI's GPT-4 model family. As of early 2025, no official GPT-5 model has been released. Operators…
- [GPT (architecture)](https://www.runlocalai.co/glossary/gpt-arch): GPT (Generative Pre-trained Transformer) is a decoder-only Transformer architecture that predicts the next token in a sequence by attending…
- [GPTQ](https://www.runlocalai.co/glossary/gptq): GPTQ (Generative Pre-trained Transformer Quantization) is a one-shot post-training quantization method that uses approximate second-order i…
- [GPU](https://www.runlocalai.co/glossary/gpu): A GPU (Graphics Processing Unit) is a specialized processor designed for parallel computation, originally for graphics but now essential fo…
- [Grouped-Query Attention (GQA)](https://www.runlocalai.co/glossary/gqa): Grouped-Query Attention (GQA) is a variant of multi-head attention that reduces memory and compute costs by sharing key-value (KV) heads ac…
- [Gradient Boosting](https://www.runlocalai.co/glossary/gradient-boosting): Gradient boosting is an ensemble machine learning technique that builds a strong predictive model by sequentially adding weak models—typica…
- [Gradient Clipping](https://www.runlocalai.co/glossary/gradient-clipping): Gradient clipping is a technique used during neural network training to prevent exploding gradients. It caps the gradient values to a maxim…
- [Gradient Descent](https://www.runlocalai.co/glossary/gradient-descent): Gradient descent is an optimization algorithm that iteratively adjusts model weights to minimize a loss function. In local AI training, it…
- [Gradio](https://www.runlocalai.co/glossary/gradio): Gradio is an open-source Python library for quickly building web-based user interfaces for machine learning models. Operators use it to cre…
- [Grok (xAI)](https://www.runlocalai.co/glossary/grok): Grok is a family of large language models (LLMs) developed by xAI, led by Elon Musk. The first version, Grok-1, was released in November 20…
- [Ground Truth](https://www.runlocalai.co/glossary/ground-truth): Ground truth is the correct, real-world answer or label that a model is trained to predict or evaluated against. In supervised learning, gr…
- [Grounding](https://www.runlocalai.co/glossary/grounding): Grounding connects a language model's output to verifiable external sources (documents, databases, APIs) to reduce hallucination. In local…
- [GSM8K](https://www.runlocalai.co/glossary/gsm8k): GSM8K is a benchmark of 8,500 grade-school math word problems requiring 2–8 reasoning steps. Models are scored by whether the final numeric…
- [Guardrails](https://www.runlocalai.co/glossary/guardrails): Guardrails are runtime constraints or filters applied to an LLM's input and output to enforce safety, compliance, or formatting rules. In l…
- [Hallucination](https://www.runlocalai.co/glossary/hallucination): Hallucination is when an LLM generates plausible-sounding but factually incorrect information — citing papers that don't exist, inventing A…
- [HBM (High Bandwidth Memory)](https://www.runlocalai.co/glossary/hbm): HBM (High Bandwidth Memory) is a 3D-stacked DRAM design that vertically layers memory dies with through-silicon vias (TSVs) to achieve much…
- [Healthcare AI](https://www.runlocalai.co/glossary/healthcare-ai): Healthcare AI refers to machine learning models applied to medical data for tasks like diagnosis, treatment planning, drug discovery, and p…
- [Hugging Face Transformers](https://www.runlocalai.co/glossary/hf-transformers): Hugging Face Transformers is a Python library that provides pre-trained models and tools for natural language processing, computer vision,…
- [HQQ (Half-Quadratic Quantization)](https://www.runlocalai.co/glossary/hqq): HQQ (Half-Quadratic Quantization) is a calibration-free quantization method that produces 2-, 3-, 4-, and 8-bit weight quantizations for tr…
- [Hugging Face](https://www.runlocalai.co/glossary/hugging-face): Hugging Face is a platform and company that hosts a vast repository of open-source machine learning models, datasets, and tools. For local…
- [Hugging Face Text Generation Inference (TGI)](https://www.runlocalai.co/glossary/huggingface-tgi): Hugging Face Text Generation Inference (TGI) is a production-grade inference server for large language models, optimized for high throughpu…
- [HumanEval](https://www.runlocalai.co/glossary/humaneval): HumanEval is a benchmark dataset of 164 hand-written programming problems, each with a function signature, docstring, and unit tests. It me…
- [Hybrid Retrieval](https://www.runlocalai.co/glossary/hybrid-retrieval): Hybrid retrieval combines dense and sparse retrieval, typically by union-then-rerank or reciprocal rank fusion (RRF). The motivation: dense…
- [Hyperparameter](https://www.runlocalai.co/glossary/hyperparameter): A hyperparameter is a configuration variable set before training begins that controls the learning process, not a parameter learned from da…
- [Hyperparameter Tuning](https://www.runlocalai.co/glossary/hyperparameter-tuning): Hyperparameter tuning is the process of selecting the configuration values that control how a model trains, such as learning rate, batch si…
- [Image Classification](https://www.runlocalai.co/glossary/image-classification): Image classification is a computer vision task where a model assigns a single label from a predefined set to an input image. For operators…
- [Image Inpainting](https://www.runlocalai.co/glossary/image-inpainting): Image inpainting is the task of filling missing or masked regions of an image with plausible, contextually consistent content. Operators en…
- [Image Segmentation](https://www.runlocalai.co/glossary/image-segmentation): Image segmentation is a computer vision task that partitions an image into multiple segments or regions, each corresponding to a distinct o…
- [ImageNet](https://www.runlocalai.co/glossary/imagenet): ImageNet is a large-scale image dataset containing over 14 million labeled images across 20,000 categories, organized by the WordNet hierar…
- [Imbalanced Data](https://www.runlocalai.co/glossary/imbalanced-data): Imbalanced data refers to a dataset where the number of samples per class is significantly skewed, with one or more minority classes having…
- [In-Context Learning](https://www.runlocalai.co/glossary/in-context-learning): In-context learning (ICL) is a capability of large language models where the model adapts its behavior based solely on examples or instruct…
- [Inference](https://www.runlocalai.co/glossary/inference): Inference is the act of running a trained model to generate predictions, as opposed to training which produces the model. For LLMs, inferen…
- [Inference API](https://www.runlocalai.co/glossary/inference-api): An inference API is a programmatic interface that accepts input data (like a prompt) and returns a model's output (like generated text) ove…
- [Inference (logical)](https://www.runlocalai.co/glossary/inference-core): Inference is the process of running a trained model on input data to generate an output — the "forward pass" that produces predictions, tex…
- [Instance Segmentation](https://www.runlocalai.co/glossary/instance-segmentation): Instance segmentation is a computer vision task that assigns a pixel-level mask to each distinct object instance in an image, while also cl…
- [Instruction Tuning](https://www.runlocalai.co/glossary/instruction-tuning): Instruction tuning is a supervised fine-tuning step where a base language model is trained on (instruction, response) pairs to improve its…
- [INT4](https://www.runlocalai.co/glossary/int4): INT4 is a quantization format that stores each model weight using 4 bits, reducing memory usage by roughly 4× compared to FP16 (16-bit) and…
- [INT8](https://www.runlocalai.co/glossary/int8): INT8 (8-bit integer) is a numerical format that uses 8 bits to represent integers, typically in the range [-128, 127] for signed or [0, 255…
- [Interpretability](https://www.runlocalai.co/glossary/interpretability): Interpretability refers to the ability to understand and explain why a model produces a specific output. For local AI operators, this matte…
- [IoU (Intersection over Union)](https://www.runlocalai.co/glossary/iou): IoU (Intersection over Union) is a metric that measures the overlap between a predicted bounding box and a ground-truth bounding box. It is…
- [Jailbreak](https://www.runlocalai.co/glossary/jailbreak): A jailbreak is a prompt designed to bypass the safety guardrails of an LLM, causing it to generate content it would normally refuse (e.g.,…
- [JAX](https://www.runlocalai.co/glossary/jax): JAX is a numerical computing library from Google that combines NumPy-like array operations with automatic differentiation and just-in-time…
- [K-Fold Cross-Validation](https://www.runlocalai.co/glossary/k-fold): K-Fold Cross-Validation is a technique for evaluating a model's performance by splitting the dataset into K equal-sized folds. The model is…
- [K-Means Clustering](https://www.runlocalai.co/glossary/k-means): K-Means Clustering is an unsupervised learning algorithm that partitions a dataset into K distinct, non-overlapping clusters. Each data poi…
- [Keras](https://www.runlocalai.co/glossary/keras): Keras is a high-level neural network API, written in Python and capable of running on top of TensorFlow, JAX, or PyTorch. It provides a use…
- [K-Nearest Neighbors (KNN)](https://www.runlocalai.co/glossary/knn): K-Nearest Neighbors (KNN) is a classical machine learning algorithm used for classification or regression. It works by finding the 'k' clos…
- [Knowledge Distillation](https://www.runlocalai.co/glossary/knowledge-distillation): Knowledge distillation is a technique where a smaller, faster 'student' model is trained to mimic the behavior of a larger, more accurate '…
- [KoboldCpp](https://www.runlocalai.co/glossary/koboldcpp): KoboldCpp is a single-file, self-contained executable that bundles llama.cpp with a web-based UI and a built-in API, designed for running l…
- [KV Cache](https://www.runlocalai.co/glossary/kv-cache): The KV cache stores the key and value tensors from previous attention computations so the model doesn't recompute them at every generated t…
- [KV Cache Quantization](https://www.runlocalai.co/glossary/kv-cache-quantization): KV cache quantization reduces the memory footprint of the key-value (KV) cache by storing its entries in lower-precision formats (e.g., 8-b…
- [LangChain](https://www.runlocalai.co/glossary/langchain): LangChain is a Python/TypeScript framework for building applications that chain together LLM calls, external data sources, and tools. It pr…
- [Language Modeling](https://www.runlocalai.co/glossary/language-modeling): Language modeling is the task of predicting the next token (word, subword, or character) in a sequence given the preceding context. In loca…
- [Latency](https://www.runlocalai.co/glossary/latency): Latency measures how fast you get a response. Two metrics matter for local LLMs:
- [Latent Diffusion](https://www.runlocalai.co/glossary/latent-diffusion): Latent diffusion is a technique used in image generation models (like Stable Diffusion) that applies the diffusion process in a compressed,…
- [Latent Space](https://www.runlocalai.co/glossary/latent-space): Latent space is the internal, compressed representation of data that a generative model learns during training. It is a lower-dimensional s…
- [Layer Normalization](https://www.runlocalai.co/glossary/layer-norm): Layer normalization is a technique that stabilizes training and inference by normalizing activations across the features of each token inde…
- [Learning Rate](https://www.runlocalai.co/glossary/learning-rate): Learning rate is a hyperparameter that controls how much the model's weights are adjusted during each training step. A high learning rate m…
- [LightGBM](https://www.runlocalai.co/glossary/lightgbm): LightGBM is a gradient boosting framework that uses tree-based learning algorithms. It is designed for efficiency and speed, especially on…
- [Linear Regression](https://www.runlocalai.co/glossary/linear-regression): Linear regression is a statistical method that models the relationship between an input variable (feature) and an output variable (target)…
- [llama.cpp](https://www.runlocalai.co/glossary/llama-cpp): llama.cpp is a C++ inference engine for running large language models (LLMs) locally on consumer hardware. It loads quantized model weights…
- [Llama (Meta)](https://www.runlocalai.co/glossary/llama-family): Llama is a family of open-weight large language models (LLMs) developed by Meta, starting with Llama 1 in 2023 and continuing through Llama…
- [LlamaIndex](https://www.runlocalai.co/glossary/llamaindex): LlamaIndex is a data framework for building retrieval-augmented generation (RAG) applications. It provides tools to ingest, index, and quer…
- [Large Language Model (LLM)](https://www.runlocalai.co/glossary/llm): A Large Language Model is a neural network with billions of parameters trained on massive text corpora to predict the next token. The "larg…
- [LLMOps](https://www.runlocalai.co/glossary/llmops): LLMOps (Large Language Model Operations) is the set of practices for deploying, monitoring, and maintaining LLMs in production. For operato…
- [LM Studio](https://www.runlocalai.co/glossary/lm-studio): LM Studio is a desktop application that provides a graphical interface for downloading, managing, and running local large language models (…
- [Logistic Regression](https://www.runlocalai.co/glossary/logistic-regression): Logistic regression is a statistical model used for binary classification tasks, predicting the probability that an input belongs to one of…
- [Logits](https://www.runlocalai.co/glossary/logits): Logits are the raw, unnormalized scores output by the final linear layer of a transformer model, before the softmax function converts them…
- [LoRA (Low-Rank Adaptation)](https://www.runlocalai.co/glossary/lora): LoRA is a parameter-efficient fine-tuning technique that adapts a large pre-trained model by training small low-rank matrices added alongsi…
- [Learning Rate Schedule](https://www.runlocalai.co/glossary/lr-schedule): A learning rate schedule adjusts the step size (learning rate) during training to improve convergence and model quality. In local AI, opera…
- [Long Short-Term Memory (LSTM)](https://www.runlocalai.co/glossary/lstm): Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture designed to model sequential data while avoiding the vanishi…
- [Machine Learning (ML)](https://www.runlocalai.co/glossary/machine-learning): Machine Learning (ML) is a field of AI where systems learn patterns from data without being explicitly programmed for every rule. In local…
- [Machine Translation](https://www.runlocalai.co/glossary/machine-translation): Machine translation (MT) is the task of automatically translating text from one natural language to another using a neural network model. O…
- [State Space Models (Mamba)](https://www.runlocalai.co/glossary/mamba): State Space Models (SSMs), notably the Mamba architecture, are a class of sequence models that process tokens in linear time relative to se…
- [mAP (mean Average Precision)](https://www.runlocalai.co/glossary/map-metric): mAP (mean Average Precision) is a metric that evaluates object detection models by averaging precision across recall thresholds for each cl…
- [MCP (Model Context Protocol)](https://www.runlocalai.co/glossary/mcp): MCP is an open protocol introduced by Anthropic in late 2024 for connecting AI agents to tools and data sources in a standardized way. Inst…
- [Markov Decision Process (MDP)](https://www.runlocalai.co/glossary/mdp): A Markov Decision Process (MDP) is a mathematical framework for modeling decision-making in environments where outcomes are partly random a…
- [Mechanistic Interpretability](https://www.runlocalai.co/glossary/mechanistic-interpretability): Mechanistic interpretability is the research approach of reverse-engineering neural networks into human-understandable algorithms by identi…
- [Medical Imaging (AI)](https://www.runlocalai.co/glossary/medical-imaging): Medical imaging AI refers to machine learning models trained to analyze medical scans like X-rays, CTs, MRIs, and pathology slides. Operato…
- [Meta AI](https://www.runlocalai.co/glossary/meta-ai): Meta AI is the artificial intelligence research division of Meta Platforms (formerly Facebook). For local AI operators, Meta AI is most rel…
- [Meta-Learning](https://www.runlocalai.co/glossary/meta-learning): Meta-learning, or 'learning to learn,' is a training paradigm where a model is exposed to many related tasks so it can quickly adapt to a n…
- [Metal (Apple)](https://www.runlocalai.co/glossary/metal): Metal is Apple's low-level GPU programming framework and API, analogous to Vulkan on other platforms. For local AI operators, Metal enables…
- [Midjourney](https://www.runlocalai.co/glossary/midjourney): Midjourney is a proprietary text-to-image AI service accessible via Discord, not a local model. Operators cannot download or run it on thei…
- [Mirostat Sampling](https://www.runlocalai.co/glossary/mirostat): Mirostat is a sampling algorithm that targets a fixed perplexity-like "surprise" level (tau) instead of a fixed top-p or top-k. The decoder…
- [Mistral](https://www.runlocalai.co/glossary/mistral-family): Mistral is a family of open-weight large language models (LLMs) developed by Mistral AI, known for their efficiency and strong performance…
- [Mixed Precision](https://www.runlocalai.co/glossary/mixed-precision): Mixed precision is a technique that uses different numerical precisions (e.g., FP16 and FP32) for different parts of a model during inferen…
- [Multi-Head Latent Attention (MLA)](https://www.runlocalai.co/glossary/mla): Multi-Head Latent Attention (MLA) is an attention mechanism used in DeepSeek V2/V3 that compresses the key-value (KV) cache into a lower-di…
- [MLC LLM](https://www.runlocalai.co/glossary/mlc-llm): MLC LLM (Machine Learning Compilation for Large Language Models) is a framework that compiles LLMs into deployable binaries for a wide rang…
- [MLflow](https://www.runlocalai.co/glossary/mlflow): MLflow is an open-source platform for managing the end-to-end machine learning lifecycle, including experimentation, reproducibility, and d…
- [MLOps](https://www.runlocalai.co/glossary/mlops): MLOps (Machine Learning Operations) is the practice of managing the lifecycle of machine learning models from development to production dep…
- [Multi-Layer Perceptron (MLP)](https://www.runlocalai.co/glossary/mlp): A Multi-Layer Perceptron (MLP) is a feedforward neural network composed of at least three layers: an input layer, one or more hidden layers…
- [MLX (Apple)](https://www.runlocalai.co/glossary/mlx): MLX is Apple's open-source array framework optimized for Apple Silicon. The Apple equivalent of PyTorch + CUDA, with first-party Metal kern…
- [MMLU](https://www.runlocalai.co/glossary/mmlu): MMLU (Massive Multitask Language Understanding) is a benchmark that tests a language model's knowledge across 57 subjects, from STEM to hum…
- [MNIST](https://www.runlocalai.co/glossary/mnist): MNIST (Modified National Institute of Standards and Technology) is a dataset of 70,000 grayscale images of handwritten digits (0–9), each 2…
- [Model Deployment](https://www.runlocalai.co/glossary/model-deployment): Model deployment is the process of making a trained AI model available for inference in a production environment. For local AI operators, t…
- [Model Monitoring](https://www.runlocalai.co/glossary/model-monitoring): Model Monitoring continuously tracks the health and performance of deployed ML models by measuring: (1) prediction quality — accuracy/F1 on…
- [Model Parallelism](https://www.runlocalai.co/glossary/model-parallelism): Model parallelism is a technique that splits a single neural network across multiple GPUs or other accelerators, with each device holding a…
- [Model Registry](https://www.runlocalai.co/glossary/model-registry): A Model Registry is a centralized catalog that stores and versions trained models along with their metadata — training dataset hash, hyperp…
- [Model Serving](https://www.runlocalai.co/glossary/model-serving): Model serving is the process of making a trained AI model available for inference via an API or local runtime. For operators running local…
- [Model Versioning](https://www.runlocalai.co/glossary/model-versioning): Model Versioning tracks the evolution of ML models over time by assigning unique identifiers to each trained artifact and its associated me…
- [Mixture of Experts (MoE)](https://www.runlocalai.co/glossary/moe): Mixture of Experts is a neural network architecture where multiple specialized sub-networks ("experts") exist, but only a subset is activat…
- [MoE Routing](https://www.runlocalai.co/glossary/moe-routing): MoE routing is the gating mechanism that decides which experts a token activates in a Mixture-of-Experts layer. Top-k routing (each token p…
- [Monte Carlo Methods](https://www.runlocalai.co/glossary/monte-carlo): Monte Carlo methods are a class of algorithms that use repeated random sampling to approximate numerical results. In local AI, they show up…
- [MPS (Metal Performance Shaders)](https://www.runlocalai.co/glossary/mps): MPS is Apple's high-level Metal-based compute library, exposed in PyTorch as the mps device backend. Calling model.to("mps") runs on the Ap…
- [Multi-Query Attention (MQA)](https://www.runlocalai.co/glossary/mqa): Multi-Query Attention (MQA) is a transformer attention variant where all attention heads share a single key/value projection instead of hav…
- [Multi-Agent System](https://www.runlocalai.co/glossary/multi-agent-system): A multi-agent system (MAS) is a setup where multiple AI agents, each with distinct roles or capabilities, collaborate or compete to solve a…
- [Multi-Head Attention](https://www.runlocalai.co/glossary/multi-head-attention): Multi-Head Attention is a mechanism in transformer models where the input is projected into multiple parallel 'attention heads,' each learn…
- [Multi-Task Learning](https://www.runlocalai.co/glossary/multi-task-learning): Multi-task learning (MTL) trains a single model on multiple related tasks simultaneously, sharing representations across tasks. In local AI…
- [Multimodal AI](https://www.runlocalai.co/glossary/multimodal): Multimodal AI refers to models that process and generate multiple data types—typically text, images, and sometimes audio or video—within a…
- [Music Generation](https://www.runlocalai.co/glossary/music-generation): Music generation refers to the use of AI models to produce audio or symbolic representations of music (e.g., MIDI, sheet music) from prompt…
- [N-gram](https://www.runlocalai.co/glossary/n-gram): An n-gram is a contiguous sequence of n items (usually tokens or characters) from a text. In local AI, n-grams appear in tokenization and l…
- [Named Entity Recognition (NER)](https://www.runlocalai.co/glossary/ner): Named Entity Recognition (NER) is an NLP task that identifies and classifies named entities (e.g., person, organization, location) in text.…
- [Neural Radiance Field (NeRF)](https://www.runlocalai.co/glossary/nerf): A Neural Radiance Field (NeRF) is a neural network that represents a 3D scene as a continuous function mapping a 3D location (x,y,z) and vi…
- [Neural Networks](https://www.runlocalai.co/glossary/neural-networks): Neural networks are the computational architecture behind modern AI models. They consist of layers of interconnected nodes (neurons) that t…
- [Natural Language Processing (NLP)](https://www.runlocalai.co/glossary/nlp): Natural Language Processing (NLP) is the field of AI focused on enabling computers to understand, interpret, and generate human language. I…
- [NLTK](https://www.runlocalai.co/glossary/nltk): NLTK (Natural Language Toolkit) is a Python library for classical NLP tasks like tokenization, stemming, tagging, and parsing. It is not a…
- [Normalization](https://www.runlocalai.co/glossary/normalization): Normalization is a data preprocessing step that rescales input values to a fixed range (e.g., [0,1] or [-1,1]) or adjusts them to have zero…
- [NPU (Neural Processing Unit)](https://www.runlocalai.co/glossary/npu): A Neural Processing Unit (NPU) is a specialized hardware accelerator designed to execute neural network operations efficiently, typically f…
- [NVIDIA](https://www.runlocalai.co/glossary/nvidia): NVIDIA designs the GPUs most operators use for local AI inference. Its consumer RTX series (e.g., RTX 4090) and workstation/enterprise card…
- [NVLink](https://www.runlocalai.co/glossary/nvlink): NVLink is NVIDIA's proprietary GPU-to-GPU interconnect, used to bind multiple data-center GPUs into a coherent memory fabric. NVLink 4 (H10…
- [NVSwitch](https://www.runlocalai.co/glossary/nvswitch): NVSwitch is the crossbar that connects 8 (or in NVL72, 72) GPUs into a single all-to-all NVLink fabric. Each GPU talks to every other GPU a…
- [Object Detection](https://www.runlocalai.co/glossary/object-detection): Object detection is a computer vision task that identifies and localizes specific objects within an image or video frame. Unlike classifica…
- [Optical Character Recognition (OCR)](https://www.runlocalai.co/glossary/ocr): Optical Character Recognition (OCR) is the process of converting images of text—scanned documents, photos, or screenshots—into machine-read…
- [Ollama](https://www.runlocalai.co/glossary/ollama): Ollama is a runtime and CLI tool for running large language models locally on consumer hardware. It wraps llama.cpp and other backends to h…
- [On-Device AI](https://www.runlocalai.co/glossary/on-device-ai): On-device AI refers to running machine learning models directly on local hardware (CPU, GPU, NPU) rather than sending data to a remote serv…
- [One-Hot Encoding](https://www.runlocalai.co/glossary/one-hot-encoding): One-hot encoding converts categorical data (e.g., token IDs) into binary vectors where only one element is 'hot' (1) and all others are 'co…
- [ONNX](https://www.runlocalai.co/glossary/onnx): ONNX (Open Neural Network Exchange) is an open-source format for representing machine learning models, designed to enable interoperability…
- [OpenAI](https://www.runlocalai.co/glossary/openai): OpenAI is the organization that developed the GPT series of large language models (GPT-3, GPT-4, GPT-4o) and the DALL-E image generation mo…
- [OpenCV](https://www.runlocalai.co/glossary/opencv): OpenCV (Open Source Computer Vision Library) is a C++ library with Python bindings for real-time image and video processing. Operators enco…
- [Orchestration (agents)](https://www.runlocalai.co/glossary/orchestration): Orchestration in the context of agents refers to the system that manages the lifecycle, communication, and task delegation among multiple A…
- [ORPO (Odds Ratio Preference Optimization)](https://www.runlocalai.co/glossary/orpo): ORPO (Odds Ratio Preference Optimization) is a fine-tuning method that combines supervised fine-tuning (SFT) and preference alignment into…
- [Overfitting](https://www.runlocalai.co/glossary/overfitting): Overfitting occurs when a model learns training data too well, including noise and irrelevant patterns, at the cost of generalizing to new…
- [PagedAttention](https://www.runlocalai.co/glossary/paged-attention): PagedAttention is the memory layout introduced by vLLM that stores the KV cache in fixed-size blocks (pages), like virtual memory. Each req…
- [pass@1](https://www.runlocalai.co/glossary/pass-at-1): pass@1 is the probability that a model's first generated solution passes the unit tests for a coding problem, computed from a single sample…
- [Pass@k](https://www.runlocalai.co/glossary/pass-at-k): Pass@k is a metric that measures the probability that at least one of k independently generated samples from a model contains a correct ans…
- [Principal Component Analysis (PCA)](https://www.runlocalai.co/glossary/pca): Principal Component Analysis (PCA) is a dimensionality reduction technique that transforms a high-dimensional dataset into a lower-dimensio…
- [Parameter-Efficient Fine-Tuning (PEFT)](https://www.runlocalai.co/glossary/peft): Parameter-Efficient Fine-Tuning (PEFT) is a set of techniques that adapt a pre-trained large language model to a specific task or domain by…
- [Perceptron](https://www.runlocalai.co/glossary/perceptron): A perceptron is the simplest form of a neural network: a single linear unit that takes weighted inputs, sums them, adds a bias, and passes…
- [Perplexity](https://www.runlocalai.co/glossary/perplexity): Perplexity is a metric that measures how well a language model predicts a sequence of tokens. Lower perplexity means the model is more conf…
- [Phi (Microsoft)](https://www.runlocalai.co/glossary/phi-family): Phi is a family of small language models (SLMs) developed by Microsoft, designed to run efficiently on consumer hardware like laptops, phon…
- [Pipeline Parallelism](https://www.runlocalai.co/glossary/pipeline-parallelism): Pipeline parallelism (a.k.a. "layer split" in llama.cpp parlance) puts whole layers on different GPUs. Card 0 handles layers 0-39; card 1 h…
- [Planning (in agents)](https://www.runlocalai.co/glossary/planning): Planning in agents refers to the process where an LLM decomposes a complex goal into a sequence of sub-steps or actions before executing th…
- [Pose Estimation](https://www.runlocalai.co/glossary/pose-estimation): Pose estimation is a computer vision task that identifies the positions of key body joints (e.g., shoulders, elbows, wrists) in an image or…
- [Positional Encoding](https://www.runlocalai.co/glossary/positional-encoding): Positional encoding is a technique used in transformer models to inject information about the position of tokens in a sequence. Unlike recu…
- [Proximal Policy Optimization (PPO)](https://www.runlocalai.co/glossary/ppo): Proximal Policy Optimization (PPO) is a reinforcement learning algorithm used to fine-tune large language models (LLMs) with human feedback…
- [Pre-training](https://www.runlocalai.co/glossary/pre-training): Pre-training is the initial phase where a large language model learns from a vast, diverse corpus of text data (e.g., web pages, books) by…
- [Precision](https://www.runlocalai.co/glossary/precision): Precision in local AI refers to the number of bits used to represent each weight and activation in a neural network. Lower precision (e.g.,…
- [Prefill (Prompt Processing)](https://www.runlocalai.co/glossary/prefill): Prefill is the first phase of LLM inference: the model processes the entire prompt in a single parallel pass, building up the KV cache for…
- [Prefix Caching](https://www.runlocalai.co/glossary/prefix-caching): Prefix caching stores the KV cache from previous requests so a new request that shares a prefix (system prompt, few-shot examples, conversa…
- [Privacy (in AI)](https://www.runlocalai.co/glossary/privacy): Privacy in local AI refers to the operator's control over their data and model interactions, ensuring no data leaves their hardware. Unlike…
- [Prompt](https://www.runlocalai.co/glossary/prompt): A prompt is the input text you provide to a language model to generate a response. It can be a simple question, a set of instructions, or a…
- [Prompt Engineering](https://www.runlocalai.co/glossary/prompt-engineering): Prompt engineering is the practice of crafting model inputs to elicit better outputs without changing the model itself. Techniques include…
- [Prompt Injection](https://www.runlocalai.co/glossary/prompt-injection): Prompt injection is a security exploit where a crafted input overrides the system prompt or instruction set of an LLM, causing it to ignore…
- [PyTorch](https://www.runlocalai.co/glossary/pytorch): PyTorch is an open-source machine learning framework developed by Meta. It provides tensor computation with GPU acceleration and automatic…
- [Q-Learning](https://www.runlocalai.co/glossary/q-learning): Q-Learning is a model-free reinforcement learning algorithm that learns an optimal action-selection policy by iteratively updating a Q-tabl…
- [Q2_K Quantization](https://www.runlocalai.co/glossary/q2-k): Q2K is 2-bit GGUF quantization averaging ~3.0 bits per parameter (with mandatory 4-bit scales and importance metadata). It exists for very…
- [Q3_K_M Quantization](https://www.runlocalai.co/glossary/q3-k-m): Q3KM is a 3-bit GGUF K-quant averaging ~3.9 bits per parameter. It's the smallest format that still produces usable output for most models.
- [Q4_0 Quantization](https://www.runlocalai.co/glossary/q4-0): Q40 is the original llama.cpp 4-bit quantization: INT4 weights with one FP16 scale per 32-element block, no zero-point, no importance matri…
- [Q4_K_M Quantization](https://www.runlocalai.co/glossary/q4-k-m): Q4KM is the most-downloaded GGUF quantization on Hugging Face — the default tradeoff for local inference. It mixes 6-bit precision on the m…
- [Q5_K_M Quantization](https://www.runlocalai.co/glossary/q5-k-m): Q5KM is a mixed-precision GGUF quantization averaging ~5.7 bits per parameter. Attention and feed-forward weights use 6-bit K-quants, the r…
- [Q8_0 Quantization](https://www.runlocalai.co/glossary/q8-0): Q80 is llama.cpp's simplest 8-bit GGUF quantization: weights in INT8, one FP16 scale per 32-element block, no zero-point. Each parameter ta…
- [QLoRA](https://www.runlocalai.co/glossary/qlora): QLoRA combines [LoRA](/glossary/lora) fine-tuning with 4-bit quantization of the base model. Introduced by Tim Dettmers in 2023, it dropped…
- [Quantization](https://www.runlocalai.co/glossary/quantization): Quantization is the process of reducing a model's numeric precision to shrink its memory footprint with minimal quality loss. A 70B-paramet…
- [Question Answering](https://www.runlocalai.co/glossary/question-answering): Question answering (QA) is a natural language processing task where a model receives a question and returns a concise answer, often extract…
- [Qwen](https://www.runlocalai.co/glossary/qwen-family): Qwen is a family of large language models (LLMs) developed by Alibaba Cloud, ranging from 0.5B to 110B parameters. Operators encounter Qwen…
- [R²](https://www.runlocalai.co/glossary/r-squared): R² (coefficient of determination) measures how well a regression model's predictions match actual outcomes, on a scale from 0 to 1. In loca…
- [Retrieval-Augmented Generation (RAG)](https://www.runlocalai.co/glossary/rag): RAG is the pattern of retrieving relevant documents from a knowledge base and including them in the LLM's prompt so the model can ground it…
- [Random Forest](https://www.runlocalai.co/glossary/random-forest): Random Forest is an ensemble machine learning method that builds multiple decision trees during training and outputs the average prediction…
- [Ray](https://www.runlocalai.co/glossary/ray): Ray is an open-source distributed computing framework for scaling AI workloads across multiple machines. Operators encounter Ray when they…
- [R-CNN family (Fast/Faster/Mask)](https://www.runlocalai.co/glossary/rcnn): The R-CNN family is a series of object detection architectures that evolved from region-based convolutional neural networks. R-CNN (Region-…
- [ReAct](https://www.runlocalai.co/glossary/react): ReAct (Reasoning + Acting) is a prompting technique that interleaves chain-of-thought reasoning with tool-use actions. In practice, the mod…
- [Reactive Agent](https://www.runlocalai.co/glossary/reactive-agent): A Reactive Agent selects actions based solely on its current percepts and a fixed set of condition-action rules, without maintaining intern…
- [Real-Time Inference](https://www.runlocalai.co/glossary/real-time-inference): Real-time inference means the model processes input and returns output fast enough to feel instantaneous to a human user — typically under…
- [Recall](https://www.runlocalai.co/glossary/recall): Recall measures the fraction of relevant items that a retrieval or classification system successfully finds. In local AI, recall appears in…
- [Recommender Systems](https://www.runlocalai.co/glossary/recommender-systems): Recommender systems are machine learning models that predict user preferences for items (movies, products, content) based on historical int…
- [Red Teaming](https://www.runlocalai.co/glossary/red-teaming): Red teaming is the practice of systematically probing an LLM to find failure modes: harmful outputs, jailbreaks, hallucinations, or policy…
- [Regularization](https://www.runlocalai.co/glossary/regularization): Regularization is a set of techniques used during model training to prevent overfitting—where the model memorizes training data instead of…
- [Reinforcement Learning (RL)](https://www.runlocalai.co/glossary/reinforcement-learning): Reinforcement Learning (RL) is a machine learning paradigm where an agent learns to make decisions by interacting with an environment, rece…
- [Representation Learning](https://www.runlocalai.co/glossary/representation-learning): Representation learning is the process by which a model automatically discovers the features or patterns in raw data that are most useful f…
- [Request Batching](https://www.runlocalai.co/glossary/request-batching): Request batching packs multiple inference requests into a single forward pass to amortize the cost of loading model weights from VRAM. Sinc…
- [Reranker (Cross-Encoder)](https://www.runlocalai.co/glossary/reranker): A reranker is a cross-encoder model that scores query/document pairs jointly (concatenated as input), producing a relevance score per pair.…
- [Residual Network (ResNet)](https://www.runlocalai.co/glossary/resnet): A Residual Network (ResNet) is a neural network architecture that introduces skip connections (also called shortcut connections) that bypas…
- [RLAIF (RL from AI Feedback)](https://www.runlocalai.co/glossary/rlaif): RLAIF (Reinforcement Learning from AI Feedback) is a technique for fine-tuning language models where an AI system, rather than a human, pro…
- [RLHF (Reinforcement Learning from Human Feedback)](https://www.runlocalai.co/glossary/rlhf): RLHF (Reinforcement Learning from Human Feedback) is a training method that fine-tunes a language model using human preferences as a reward…
- [RMSNorm](https://www.runlocalai.co/glossary/rms-norm): RMSNorm is a simpler variant of LayerNorm that normalizes activations by their root-mean-square instead of their variance, skipping the mea…
- [Recurrent Neural Network (RNN)](https://www.runlocalai.co/glossary/rnn): A Recurrent Neural Network (RNN) is a neural network architecture designed for sequential data, where each output depends on the previous h…
- [Robotics (AI)](https://www.runlocalai.co/glossary/robotics): Robotics in AI refers to the integration of machine learning models into physical robots to enable perception, decision-making, and control…
- [ROC Curve](https://www.runlocalai.co/glossary/roc): A Receiver Operating Characteristic (ROC) curve plots the true positive rate against the false positive rate at various classification thre…
- [ROCm (AMD)](https://www.runlocalai.co/glossary/rocm): ROCm (Radeon Open Compute) is AMD's open-source equivalent of NVIDIA's CUDA. It's required for any meaningful AMD GPU inference — vLLM ROCm…
- [Rotary Position Embedding (RoPE)](https://www.runlocalai.co/glossary/rope): Rotary Position Embedding (RoPE) is a method for encoding token position in transformer models by rotating query and key vectors in attenti…
- [Robotic Process Automation (RPA)](https://www.runlocalai.co/glossary/rpa): Robotic Process Automation (RPA) is software that automates repetitive, rule-based tasks typically performed by humans interacting with gra…
- [Sampling (Decoding)](https://www.runlocalai.co/glossary/sampling): Sampling is the process of converting model logits into output tokens. Common strategies: greedy (temperature 0), random sampling (temperat…
- [scikit-learn](https://www.runlocalai.co/glossary/scikit-learn): scikit-learn is a Python library for classical machine learning (regression, classification, clustering, dimensionality reduction) built on…
- [Random Seed](https://www.runlocalai.co/glossary/seed): A random seed initializes the pseudo-random generator that drives sampling at temperature  0. Same seed + same prompt + same settings + sam…
- [Self-Attention](https://www.runlocalai.co/glossary/self-attention): Self-attention computes a weighted representation of every position in a sequence by comparing each token against every other token within…
- [Self-Driving Cars](https://www.runlocalai.co/glossary/self-driving-cars): Self-driving cars, also known as autonomous vehicles, use AI to perceive their environment and navigate without human input. They rely on s…
- [Self-Supervised Learning](https://www.runlocalai.co/glossary/self-supervised-learning): Self-supervised learning (SSL) is a training paradigm where a model learns representations from unlabeled data by creating its own supervis…
- [Semantic Search](https://www.runlocalai.co/glossary/semantic-search): Semantic search retrieves results based on meaning rather than exact keyword matches. Instead of looking for literal word occurrences, it c…
- [Semantic Segmentation](https://www.runlocalai.co/glossary/semantic-segmentation): Semantic segmentation is a computer vision task that assigns a class label (e.g., 'car', 'road', 'person') to every pixel in an image. Unli…
- [Sensitivity](https://www.runlocalai.co/glossary/sensitivity): Sensitivity measures how much a model's output changes in response to small changes in its input. In local AI, sensitivity is relevant when…
- [Sentiment Analysis](https://www.runlocalai.co/glossary/sentiment-analysis): Sentiment analysis is a text classification task where a model assigns a label (e.g., positive, negative, neutral) to a piece of text based…
- [Stochastic Gradient Descent (SGD)](https://www.runlocalai.co/glossary/sgd): Stochastic Gradient Descent (SGD) is an optimization algorithm used during model training to minimize the loss function. Unlike standard gr…
- [SGLang](https://www.runlocalai.co/glossary/sglang): SGLang is an open-source LLM inference engine focused on high throughput for structured generation and complex agent workflows. It implemen…
- [Shadow Deployment](https://www.runlocalai.co/glossary/shadow-deployment): Shadow Deployment (also called dark launch or shadow mode) runs a candidate model in production alongside the current model, feeding it ide…
- [SLAM](https://www.runlocalai.co/glossary/slam): SLAM (Simultaneous Localization and Mapping) is a computational problem in robotics and computer vision where a device builds a map of an u…
- [Sliding Window Attention (SWA)](https://www.runlocalai.co/glossary/sliding-window-attention): Sliding Window Attention (SWA) is an attention pattern where each token only attends to a fixed-size window of nearby tokens rather than th…
- [spaCy](https://www.runlocalai.co/glossary/spacy): spaCy is a Python library for industrial-strength natural language processing (NLP) that provides pre-trained pipelines for tokenization, p…
- [Sparse Retrieval](https://www.runlocalai.co/glossary/sparse-retrieval): Sparse retrieval scores documents by lexical overlap with the query — high-dimensional vectors where most entries are zero. BM25 is the can…
- [Speculative Decoding](https://www.runlocalai.co/glossary/speculative-decoding): Speculative decoding speeds up LLM inference by using a small fast "draft" model to propose the next several tokens, then verifying them al…
- [Speech Processing](https://www.runlocalai.co/glossary/speech-processing): Speech processing refers to the analysis, synthesis, and manipulation of human speech by AI models. Operators encounter it when running aut…
- [Speech Synthesis](https://www.runlocalai.co/glossary/speech-synthesis): Speech synthesis, also known as text-to-speech (TTS), converts written text into spoken audio. In local AI, operators run TTS models like P…
- [Stability AI](https://www.runlocalai.co/glossary/stability-ai): Stability AI is the company behind the Stable Diffusion family of image generation models, which operators run locally via tools like Comfy…
- [Stable Diffusion](https://www.runlocalai.co/glossary/stable-diffusion): Stable Diffusion is a text-to-image model that generates images from text prompts using a diffusion process. It runs on consumer GPUs with…
- [Standardization](https://www.runlocalai.co/glossary/standardization): Standardization in local AI refers to the process of converting raw data into a consistent format that models can process reliably. For ope…
- [Streamlit](https://www.runlocalai.co/glossary/streamlit): Streamlit is an open-source Python framework for turning data scripts into interactive web apps with minimal code. Operators encounter it w…
- [Style Transfer](https://www.runlocalai.co/glossary/style-transfer): Style transfer is a computer vision technique that applies the visual style of one image (e.g., a painting) to the content of another image…
- [StyleGAN](https://www.runlocalai.co/glossary/stylegan): StyleGAN is a generative adversarial network (GAN) architecture designed for high-resolution image synthesis, introduced by NVIDIA in 2018.…
- [Super-Resolution](https://www.runlocalai.co/glossary/super-resolution): Super-resolution is a computer vision technique that takes a low-resolution image and generates a higher-resolution version by inferring mi…
- [Supervised Learning](https://www.runlocalai.co/glossary/supervised-learning): Supervised learning is a training paradigm where a model learns to map inputs to outputs using labeled data — each training example pairs a…
- [Support Vector Machine (SVM)](https://www.runlocalai.co/glossary/svm): A Support Vector Machine (SVM) is a supervised learning model that finds a hyperplane (a decision boundary) to separate data into classes w…
- [SwiGLU](https://www.runlocalai.co/glossary/swiglu): SwiGLU is a gated feed-forward activation: (W1·x ⊙ swish(W2·x)) · W3, replacing the standard MLP's GELU/ReLU in modern transformers. Used i…
- [Sycophancy](https://www.runlocalai.co/glossary/sycophancy): Sycophancy in LLMs refers to the model's tendency to agree with a user's stated or implied position, even when that position is incorrect o…
- [Synthetic Data](https://www.runlocalai.co/glossary/synthetic-data): Synthetic data is artificially generated data used to train or fine-tune AI models, created by algorithms rather than collected from real-w…
- [System Prompt](https://www.runlocalai.co/glossary/system-prompt): A system prompt is the initial instruction or context prepended to a conversation with an LLM. It sets the model's behavior, persona, outpu…
- [T5](https://www.runlocalai.co/glossary/t5): T5 (Text-to-Text Transfer Transformer) is a sequence-to-sequence model from Google that converts every NLP task into a text-to-text format.…
- [Temperature (sampling)](https://www.runlocalai.co/glossary/temperature): Temperature is a sampling parameter that controls the randomness of token selection during text generation. It scales the logits (raw score…
- [Temperature 0 (Greedy Sampling)](https://www.runlocalai.co/glossary/temperature-zero): Temperature 0 disables sampling entirely — the model picks the highest-logit token at every step. Equivalent to greedy decoding with topk=1…
- [Tensor Core](https://www.runlocalai.co/glossary/tensor-core): Tensor Cores are specialized hardware units on NVIDIA GPUs (Volta architecture and later) that perform fused multiply-add (FMA) operations…
- [Tensor Parallelism](https://www.runlocalai.co/glossary/tensor-parallelism): Tensor parallelism splits each transformer layer's weight matrices across multiple GPUs. Card 0 holds the first half of every weight tensor…
- [TensorBoard](https://www.runlocalai.co/glossary/tensorboard): TensorBoard is a visualization toolkit from TensorFlow for inspecting model training metrics, graph structures, and weight histograms. Oper…
- [TensorFlow](https://www.runlocalai.co/glossary/tensorflow): TensorFlow is an open-source machine learning framework developed by Google. Operators encounter it as an alternative to PyTorch for traini…
- [TensorRT](https://www.runlocalai.co/glossary/tensorrt): TensorRT is NVIDIA's SDK for optimizing and deploying deep learning models on NVIDIA GPUs. It performs graph optimization, kernel fusion, a…
- [Test Data](https://www.runlocalai.co/glossary/test-data): Test data is a set of examples used to evaluate a model's performance after training, distinct from the training data the model learned fro…
- [Text Classification](https://www.runlocalai.co/glossary/text-classification): Text classification is a natural language processing task where a model assigns a predefined category label to a piece of text. Operators e…
- [Text Generation](https://www.runlocalai.co/glossary/text-generation): Text generation is the process where a language model produces coherent sequences of tokens (words or subwords) in response to a prompt. In…
- [text-generation-webui (oobabooga)](https://www.runlocalai.co/glossary/text-generation-webui): text-generation-webui (often called oobabooga) is a browser-based interface for running large language models locally. It wraps multiple ba…
- [Text Summarization](https://www.runlocalai.co/glossary/text-summarization): Text summarization is a natural language processing task where a model generates a shorter version of a longer text while preserving key in…
- [Throughput](https://www.runlocalai.co/glossary/throughput): Throughput measures how much work a system completes per unit time — typically tokens-per-second across all concurrent requests. Distinct f…
- [Throughput vs Latency](https://www.runlocalai.co/glossary/throughput-vs-latency): Throughput is aggregate tokens generated per second across all in-flight requests; latency is wall-clock time for a single request (TTFT +…
- [Token](https://www.runlocalai.co/glossary/token): A token is the smallest unit of text a language model processes. Most modern models use subword tokenization, where common words map to sin…
- [Tokenization](https://www.runlocalai.co/glossary/tokenization): Tokenization is the process of converting text into the numeric tokens a model can process. Modern systems use subword tokenization (BPE, W…
- [Tokens per second](https://www.runlocalai.co/glossary/tokens-per-sec): Tokens per second (tok/s) is the most-cited LLM throughput metric, but it's also the most-misunderstood. It splits into two distinct phases…
- [Tool calling](https://www.runlocalai.co/glossary/tool-calling): Tool calling (also called function calling) is a model's structured output capability where it produces JSON-shaped tool invocations instea…
- [Top-k Sampling](https://www.runlocalai.co/glossary/top-k-sampling): Top-k sampling is a text-generation strategy that restricts the model's next-token choices to the k tokens with the highest probabilities.…
- [Top-p (Nucleus) Sampling](https://www.runlocalai.co/glossary/top-p-sampling): Top-p (nucleus) sampling is a text generation strategy that selects from the smallest set of tokens whose cumulative probability exceeds a…
- [Topic Modeling](https://www.runlocalai.co/glossary/topic-modeling): Topic modeling is an unsupervised NLP technique that discovers latent themes (topics) across a collection of documents. It treats each docu…
- [TPU (Tensor Processing Unit)](https://www.runlocalai.co/glossary/tpu): A Tensor Processing Unit (TPU) is a custom ASIC designed by Google specifically for accelerating machine learning workloads, particularly m…
- [Quantization](https://www.runlocalai.co/glossary/training): Quantization is the process of reducing a model's numeric precision to shrink its memory footprint with minimal quality loss. A 70B-paramet…
- [Training Data](https://www.runlocalai.co/glossary/training-data): Training data is the dataset used to teach a model its patterns and behaviors. For LLMs, this typically means trillions of tokens of text s…
- [Transfer Learning](https://www.runlocalai.co/glossary/transfer-learning): Transfer learning is a technique where a model trained on one task is reused as the starting point for a second task. In local AI, this mea…
- [Transformer](https://www.runlocalai.co/glossary/transformer): The Transformer is a neural network architecture introduced in 2017 that replaced recurrent layers with a self-attention mechanism, enablin…
- [Transparency (AI)](https://www.runlocalai.co/glossary/transparency): Transparency in AI refers to the degree to which a model's behavior, training data, architecture, and decision-making processes are open to…
- [Tree of Thoughts](https://www.runlocalai.co/glossary/tree-of-thoughts): Tree of Thoughts (ToT) is a prompting strategy that expands a single chain of reasoning into a tree of multiple reasoning paths, evaluating…
- [Triton Inference Server](https://www.runlocalai.co/glossary/triton): Triton Inference Server is an open-source inference serving software by NVIDIA that manages multiple AI models across GPU and CPU hardware,…
- [t-SNE](https://www.runlocalai.co/glossary/tsne): t-SNE (t-distributed Stochastic Neighbor Embedding) is a dimensionality reduction technique used to visualize high-dimensional data (like e…
- [Time to first token (TTFT)](https://www.runlocalai.co/glossary/ttft): TTFT (time-to-first-token) is the latency between sending a prompt and receiving the first generated token. It's dominated by the prefill p…
- [Text-to-Speech (TTS)](https://www.runlocalai.co/glossary/tts): Text-to-Speech (TTS) converts written text into spoken audio using neural models. Operators encounter TTS when running local models like Pi…
- [U-Net](https://www.runlocalai.co/glossary/u-net): U-Net is a convolutional neural network architecture designed for image segmentation tasks. It consists of a contracting (encoder) path tha…
- [UMAP](https://www.runlocalai.co/glossary/umap): UMAP (Uniform Manifold Approximation and Projection) is a dimensionality reduction technique used to visualize high-dimensional data, such…
- [Unified Memory](https://www.runlocalai.co/glossary/unified-memory): Unified memory is a memory architecture where CPU and GPU share the same physical RAM pool, eliminating CPU↔GPU copies. Apple Silicon and A…
- [Unsupervised Learning](https://www.runlocalai.co/glossary/unsupervised-learning): Unsupervised learning is a machine learning paradigm where a model finds patterns in data without labeled examples. Unlike supervised learn…
- [Variational Autoencoder (VAE)](https://www.runlocalai.co/glossary/vae): A Variational Autoencoder (VAE) is a generative neural network that learns a compressed latent representation of input data (like images) a…
- [Validation Data](https://www.runlocalai.co/glossary/validation-data): Validation data is a subset of examples held back from training to evaluate how well a model generalizes to unseen inputs. During training,…
- [Vanishing Gradient](https://www.runlocalai.co/glossary/vanishing-gradient): The vanishing gradient problem occurs when gradients used to update model weights become extremely small as they are backpropagated through…
- [Vector Database](https://www.runlocalai.co/glossary/vector-database): A vector database stores and retrieves data as high-dimensional vectors (embeddings) rather than rows or documents. In local AI, it enables…
- [Video Generation](https://www.runlocalai.co/glossary/video-generation): Video generation refers to the process of creating new video content from text prompts, images, or other video inputs using generative AI m…
- [Vision Transformer (ViT)](https://www.runlocalai.co/glossary/vit): A Vision Transformer (ViT) is a neural network architecture that applies the Transformer model, originally designed for text, directly to i…
- [vLLM](https://www.runlocalai.co/glossary/vllm): vLLM is an open-source inference engine optimized for high-throughput, low-latency serving of large language models. It implements PagedAtt…
- [Vision-Language Model (VLM)](https://www.runlocalai.co/glossary/vlm): A Vision-Language Model (VLM) processes both images and text, enabling tasks like image captioning, visual question answering, and document…
- [Voice Cloning](https://www.runlocalai.co/glossary/voice-cloning): Voice cloning is the process of generating synthetic speech that mimics a specific person's voice, including timbre, pitch, and speaking st…
- [VRAM (Video RAM)](https://www.runlocalai.co/glossary/vram): VRAM is the dedicated memory on a GPU. For local AI, VRAM capacity is the single most important spec — it determines which models you can l…
- [VRAM Bandwidth](https://www.runlocalai.co/glossary/vram-bandwidth): VRAM bandwidth is the rate at which the GPU's video memory can transfer data to the compute cores, measured in GB/s. For local LLM inferenc…
- [Vulkan compute](https://www.runlocalai.co/glossary/vulkan): Vulkan compute is a cross-platform GPU compute API that runs inference workloads on GPUs without requiring CUDA. In local AI, it allows ope…
- [Vulkan Compute](https://www.runlocalai.co/glossary/vulkan-compute): Vulkan compute is the cross-vendor GPU compute API from Khronos. llama.cpp ships a Vulkan backend that runs on AMD, Intel, and NVIDIA GPUs…
- [Weights & Biases](https://www.runlocalai.co/glossary/wandb): Weights & Biases (W&B) is a cloud-based MLOps platform for tracking experiments, visualizing metrics, and managing model artifacts. Operato…
- [Weight Decay](https://www.runlocalai.co/glossary/weight-decay): Weight decay is a regularization technique used during model training that adds a penalty proportional to the squared magnitude of the weig…
- [Word Embedding](https://www.runlocalai.co/glossary/word-embedding): A word embedding is a dense vector of floating-point numbers that maps a word (or token) to a point in a high-dimensional space. In practic…
- [Word2Vec](https://www.runlocalai.co/glossary/word2vec): Word2Vec is an algorithm that learns dense vector representations (embeddings) of words from large text corpora. Each word maps to a fixed-…
- [XAI (Explainable AI)](https://www.runlocalai.co/glossary/xai): Explainable AI (XAI) refers to methods that make the decisions of machine learning models understandable to humans. For local AI operators,…
- [XGBoost](https://www.runlocalai.co/glossary/xgboost): XGBoost (Extreme Gradient Boosting) is a gradient-boosted decision tree (GBDT) library optimized for structured/tabular data. It builds an…
- [YaRN (Yet another RoPE eNlargement)](https://www.runlocalai.co/glossary/yarn): YaRN is a context-extension method that modifies RoPE frequencies to let a model trained on, say, 8K context generalize to 32K or 128K with…
- [YOLO](https://www.runlocalai.co/glossary/yolo): YOLO (You Only Look Once) is a family of real-time object detection models that process an entire image in a single forward pass, directly…
- [ZeRO optimizer](https://www.runlocalai.co/glossary/zero): ZeRO (Zero Redundancy Optimizer) is a memory optimization technique for distributed training of large models. It partitions optimizer state…
- [Zero-Shot Learning](https://www.runlocalai.co/glossary/zero-shot-learning): Zero-shot learning is a capability where a model performs a task it was never explicitly trained on, using only a natural-language descript…
- [Zero-Shot Prompting](https://www.runlocalai.co/glossary/zero-shot-prompting): Zero-shot prompting is a technique where you give a language model a task description or instruction without providing any examples of the…

## Error fixes (56)
- [RuntimeError: CUDA error: device-side assert triggered](https://www.runlocalai.co/errors/cuda-device-side-assert)
- [PyTorch CUDA error: driver version is insufficient for CUDA runtime](https://www.runlocalai.co/errors/cuda-driver-pytorch-mismatch)
- [CUDA driver version is insufficient for CUDA runtime version](https://www.runlocalai.co/errors/cuda-driver-version-insufficient)
- [CUDA OOM that only happens at long context (KV cache blowup)](https://www.runlocalai.co/errors/cuda-oom-kv-cache-blowup)
- [vLLM AsyncEngineDeadError after large batch / OOM](https://www.runlocalai.co/errors/cuda-oom-large-batch)
- [CUDA out of memory when loading a model](https://www.runlocalai.co/errors/cuda-out-of-memory)
- [CUDA runtime version doesn't match the installed driver](https://www.runlocalai.co/errors/cuda-runtime-driver-version-mismatch)
- [Docker: could not select device driver "nvidia"](https://www.runlocalai.co/errors/docker-gpu-could-not-select-device-driver)
- [Docker: could not select device driver "" with capabilities: [[gpu]]](https://www.runlocalai.co/errors/docker-gpu-passthrough)
- [exllamav2 ImportError: cannot import name 'ExLlamaV2' / undefined symbol](https://www.runlocalai.co/errors/exllamav2-import-error)
- [flash-attn install fails on Windows / no precompiled wheel](https://www.runlocalai.co/errors/flash-attn-install-windows)
- [Token generation slows as conversation gets longer](https://www.runlocalai.co/errors/generation-slows-as-context-grows)
- [GGUF model outputs garbage — tokenizer / chat-template mismatch](https://www.runlocalai.co/errors/gguf-tokenizer-mismatch-chat-template)
- [Failed to load model: GGUF version mismatch](https://www.runlocalai.co/errors/gguf-version-mismatch)
- [HuggingFace: 403 Forbidden when downloading a gated model](https://www.runlocalai.co/errors/huggingface-403-forbidden)
- [Model loaded but tokenizer vocab size mismatch](https://www.runlocalai.co/errors/huggingface-config-vocab-mismatch)
- [HuggingFace download is extremely slow or stalls](https://www.runlocalai.co/errors/huggingface-download-too-slow)
- [Process killed (OOM killer) when loading large model](https://www.runlocalai.co/errors/killed-oom-killer)
- [Out of memory specifically at long context lengths](https://www.runlocalai.co/errors/kv-cache-oom-long-context)
- [llama.cpp: error loading model — bad magic / unsupported GGUF](https://www.runlocalai.co/errors/llama-cpp-bad-magic-gguf-format)
- [llama.cpp CUDA build: unsupported GNU version! gcc versions later than X are not supported](https://www.runlocalai.co/errors/llama-cpp-build-gcc-version)
- [llama.cpp build fails: nvcc not found / CUDA toolkit missing](https://www.runlocalai.co/errors/llama-cpp-build-missing-cuda-toolkit)
- [llama.cpp build fails: nvcc not found](https://www.runlocalai.co/errors/llama-cpp-cuda-build-nvcc-not-found)
- [llama.cpp: failed to mmap GGUF file](https://www.runlocalai.co/errors/llama-cpp-failed-to-mmap)
- [LM Studio generation much slower than expected](https://www.runlocalai.co/errors/lm-studio-slow-tokens-per-sec)
- [Very slow first token / OOM only at long prompts](https://www.runlocalai.co/errors/long-context-prefill-latency)
- [Metal Allocator: out of memory on Apple Silicon](https://www.runlocalai.co/errors/metal-oom-apple-silicon-mlx)
- [Metal allocation failed — Apple Silicon OOM under unified memory pressure](https://www.runlocalai.co/errors/metal-out-of-memory)
- [OSError: Can't load tokenizer for ... / no file named tokenizer.json](https://www.runlocalai.co/errors/missing-tokenizer-files)
- [MLX: Memory pressure detected — consider reducing batch size](https://www.runlocalai.co/errors/mlx-memory-pressure-batch-size)
- [MLX / Metal: command buffer execution failed](https://www.runlocalai.co/errors/mlx-metal-command-buffer-error)
- [Apple Silicon: RuntimeError: MPS backend out of memory](https://www.runlocalai.co/errors/mps-backend-out-of-memory)
- [NCCL error: peer to peer not supported (multi-GPU)](https://www.runlocalai.co/errors/nccl-peer-to-peer-not-supported)
- [Ollama can't bind port 11434 — already in use](https://www.runlocalai.co/errors/ollama-bind-port-conflict)
- [Ollama: connection refused on localhost:11434](https://www.runlocalai.co/errors/ollama-connection-refused)
- [Ollama: model requires more system memory than is available](https://www.runlocalai.co/errors/ollama-insufficient-memory)
- [Ollama: listen tcp 127.0.0.1:11434 bind: address already in use](https://www.runlocalai.co/errors/ollama-listen-tcp-11434-bind-systemd)
- [Ollama: Error: model 'X' not found](https://www.runlocalai.co/errors/ollama-model-not-found)
- [Open WebUI: Failed to fetch from /ollama (cannot reach Ollama backend)](https://www.runlocalai.co/errors/open-webui-cannot-connect-ollama)
- [Q2_K or Q3 quantized model produces nonsense](https://www.runlocalai.co/errors/q2-quantization-garbage-output)
- [Quantized model produces garbage / never stops generating](https://www.runlocalai.co/errors/quantized-model-wrong-chat-template)
- [ROCm: HSA_STATUS_ERROR_INVALID_DEVICE — GPU not detected](https://www.runlocalai.co/errors/rocm-device-not-found)
- [ROCm: HIP error: invalid device function](https://www.runlocalai.co/errors/rocm-hip-invalid-device-function)
- [ROCm: hipErrorInvalidDeviceFunction on RX 7000-series](https://www.runlocalai.co/errors/rocm-invalid-device-function-rdna3)
- [ROCm: HIP error: invalid device — no GPU detected](https://www.runlocalai.co/errors/rocm-no-gpu-detected)
- [SGLang: RadixAttention KV cache overflow / out of memory](https://www.runlocalai.co/errors/sglang-radix-attention-kv-cache-overflow)
- [Slow tokens/sec on capable GPU (silent CPU fallback)](https://www.runlocalai.co/errors/slow-tokens-cpu-fallback)
- [Model produces gibberish or repeats one token forever](https://www.runlocalai.co/errors/tokenizer-mismatch-gibberish-output)
- [TypeError: 'NoneType' object is not subscriptable in tokenizer](https://www.runlocalai.co/errors/tokenizer-nonetype-not-subscriptable)
- [PyTorch: CUDA error: no kernel image is available for execution on the device](https://www.runlocalai.co/errors/torch-cuda-initialization-error)
- [vLLM install picks the wrong CUDA wheel](https://www.runlocalai.co/errors/vllm-cuda-wheel-mismatch-extra-index-url)
- [vLLM: No available KV cache blocks](https://www.runlocalai.co/errors/vllm-no-available-kv-cache-blocks)
- [Windows DirectML model runs on CPU instead of GPU](https://www.runlocalai.co/errors/windows-directml-cpu-fallback)
- [WSL2: nvidia-smi works but PyTorch sees no CUDA / libcuda.so missing](https://www.runlocalai.co/errors/wsl2-gpu-access-broken)
- [WSL2 GPU not detected — nvidia-smi missing or empty](https://www.runlocalai.co/errors/wsl2-gpu-not-detected)
- [WSL2: torch.cuda.is_available() returns False](https://www.runlocalai.co/errors/wsl2-torch-cuda-not-available)

## Local AI apps (39)
- [Aider](https://www.runlocalai.co/apps/aider): Aider is for developers who work in the terminal and want a coding agent that respects their existing workflow. It connects to any OpenAI-c…
- [AnythingLLM](https://www.runlocalai.co/apps/anythingllm): AnythingLLM is for anyone who needs to turn a folder of PDFs, markdown files, or plain text into a working RAG chatbot in minutes. Its work…
- [AutoGen](https://www.runlocalai.co/apps/autogen): AutoGen is for developers who need to decompose a complex task into role-played agent conversations—a coder agent, a reviewer agent, a plan…
- [Buzz](https://www.runlocalai.co/apps/buzz): Buzz is the right choice if you need offline Whisper transcription on Linux, Windows, or macOS and want to keep your audio data local. It b…
- [Claudin.io](https://www.runlocalai.co/apps/claudin-io): Claudin.io is a cloud routing proxy that sits between your application and a pool of upstream LLM providers (Anthropic, OpenAI, open-weight…
- [Cline](https://www.runlocalai.co/apps/cline): Cline is the VS Code extension for solo Ollama users who want a full agent loop—plan, read, edit, run, verify—without shipping code to a cl…
- [Codeium (with local backend)](https://www.runlocalai.co/apps/codeium-local): For teams that must keep code off third-party clouds, Codeium’s self-hosted backend is the most polished way to get Copilot-grade autocompl…
- [Continue](https://www.runlocalai.co/apps/continue-dev): For solo Ollama users who want a single VS Code or JetBrains extension that handles autocomplete, inline chat, and edit-by-prompt, Continue…
- [CrewAI](https://www.runlocalai.co/apps/crewai): CrewAI is for developers who want to orchestrate multiple local models into role-based workflows without fighting framework defaults. It br…
- [Diffusion Bee](https://www.runlocalai.co/apps/diffusionbee): For macOS users who want to generate images without touching a terminal or config file, Diffusion Bee is the fastest path to a first image.…
- [Draw Things](https://www.runlocalai.co/apps/drawthings): Draw Things is the pick for anyone who wants Stable Diffusion or Flux on an iPhone or MacBook without touching Python or a cloud service. I…
- [Enchanted](https://www.runlocalai.co/apps/enchanted): For solo Ollama users who want a chat interface that feels native to Apple hardware, Enchanted delivers. It connects to your home or lab Ol…
- [GPT4All](https://www.runlocalai.co/apps/gpt4all): GPT4All is the pick for users who want a fully MIT-licensed desktop AI that stays entirely offline, with no telemetry or cloud dependencies…
- [Jan](https://www.runlocalai.co/apps/jan): Jan is the right pick if you want a local chat app that works without touching a terminal or Docker. It ships as a single desktop binary fo…
- [Khoj](https://www.runlocalai.co/apps/khoj): For solo users running Ollama on a laptop or desktop, Khoj turns local notes, emails, and PDFs into a searchable chat interface. It bridges…
- [Khoj CLI](https://www.runlocalai.co/apps/khoj-cli): For solo Ollama users who live in the terminal, Khoj CLI turns your shell into a local document assistant. Pipe any text—grep output, log f…
- [Krita AI Diffusion](https://www.runlocalai.co/apps/krita-ai-diffusion): For digital artists who already live inside Krita and want Stable Diffusion as a native brush, not a separate chat interface. This plugin b…
- [LangChain](https://www.runlocalai.co/apps/langchain): LangChain is the default pick if you want a framework that ships with working defaults for retrieval, tool-calling, and memory — and you do…
- [Leo (Brave)](https://www.runlocalai.co/apps/leo-brave): For Brave users who already keep a local Ollama instance running, Leo is the fastest path to a browser-native AI assistant that doesn't pho…
- [LibreChat](https://www.runlocalai.co/apps/librechat): LibreChat is for teams or power users who want a single interface that bridges local Ollama models with cloud APIs like Anthropic and OpenA…
- [LiteLLM](https://www.runlocalai.co/apps/litellm): LiteLLM is the right choice when you need to swap between local Ollama or llama.cpp and cloud providers like Anthropic or Gemini without re…
- [LlamaIndex](https://www.runlocalai.co/apps/llamaindex): LlamaIndex is the framework to reach for when your primary workload is retrieval-augmented generation over a document corpus. It bridges di…
- [LM Studio](https://www.runlocalai.co/apps/lm-studio-app): LM Studio is the default pick for anyone who wants to run open-weight models locally without touching a terminal. It bundles a model catalo…
- [MacWhisper](https://www.runlocalai.co/apps/macwhisper): MacWhisper is for macOS users who want Whisper transcription without touching a terminal or managing Python environments. It wraps whisper-…
- [Maid](https://www.runlocalai.co/apps/maid): Maid is for anyone who wants to chat with local models on Android without being locked to a single runtime. It bridges to a remote Ollama s…
- [Msty](https://www.runlocalai.co/apps/msty): Msty is for anyone who regularly asks the same question to a local model and a cloud API, then compares outputs side by side. It bridges Ol…
- [Obsidian Copilot](https://www.runlocalai.co/apps/obsidian-copilot): Obsidian Copilot is the plugin to pick if you keep your notes in Obsidian and want a local LLM wired directly into your writing flow. It br…
- [Odysseus](https://www.runlocalai.co/apps/odysseus): Odysseus is a free, open-source, self-hosted AI workspace from Felix Kjellberg (PewDiePie), released May 31, 2026 under the MIT license. It…
- [Ollama JS / TS SDK](https://www.runlocalai.co/apps/ollama-js): For Node and browser developers who want a typed, streaming bridge to Ollama without reinventing HTTP calls. This is the official SDK, so i…
- [Ollama Python SDK](https://www.runlocalai.co/apps/ollama-python): For solo Ollama users writing Python scripts or small services, this is the SDK to reach for. It bridges directly to a local Ollama server…
- [Open WebUI](https://www.runlocalai.co/apps/open-webui): Open WebUI is the default chat interface for solo Ollama users who want a ChatGPT-like experience without sending data anywhere. It bridges…
- [OpenedAI-Speech](https://www.runlocalai.co/apps/openedai-speech): For teams already wired to OpenAI’s TTS API, OpenedAI-Speech is the most direct path to fully offline voice synthesis. It accepts the same…
- [Page Assist](https://www.runlocalai.co/apps/page-assist): For solo Ollama users who want a browser sidebar that actually talks to their local models, Page Assist is the cleanest integration availab…
- [PrivateGPT](https://www.runlocalai.co/apps/privategpt): PrivateGPT is the right choice when your compliance posture demands a truly air-gapped RAG pipeline. It bridges to Ollama, llama.cpp, or an…
- [Reor](https://www.runlocalai.co/apps/reor): Reor is for Ollama users who want their note-taking app to actively connect ideas rather than just store them. It runs a local LLM and embe…
- [Smart Connections (Obsidian)](https://www.runlocalai.co/apps/smart-connections): For solo note-takers running Ollama on a laptop, Smart Connections turns Obsidian into a local semantic search engine. It embeds each note…
- [Tabby](https://www.runlocalai.co/apps/tabby): Tabby is the coding agent server you pick when you’re not just running local models for yourself, but deploying them to a team of 20 or mor…
- [Twinny](https://www.runlocalai.co/apps/twinny): Twinny is for solo Ollama users who want a Copilot replacement without the configuration overhead. It bridges directly to Ollama, deliverin…
- [Verba](https://www.runlocalai.co/apps/verba): Verba is for teams that want to ship an internal-doc chat app without debating chunking strategies or vector store choices. Point it at you…