The frontier of open-weight model releases
Open-weight model releases tracked by RunLocalAI — recent additions, rising families, distill chains, multimodal and reasoning waves. Each card links into the catalog with authority badges (L1.25 enriched · benchmark-backed · verdict) so you can scan editorial coverage at a glance.
Filtered results (46)
Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.
Mistral Medium 3 24B (dense)
research / non-commercial workstation deployments
Granite 3.3 8B
enterprise tool-calling on IBM stacks
Mistral Small 3.2 24B
consumer-tier multilingual instruction-following
Nemotron 3 Nano 9B
NVIDIA-stack tool-calling agents
Nemotron 3 Nano (30B-A3B)
NVIDIA-tuned consumer-tier general
DeepSeek V3 Lite (16B MoE)
consumer-tier MoE inference
EXAONE 3.5 8B
consumer-tier Korean workloads
InternLM 3 8B
Chinese-language consumer workloads
Devstral Small 2 24B
Apache 2.0 coding alternative to Qwen 2.5 Coder
Yi Coder 9B
8GB-VRAM coding
Qwen 3 7B
consumer-tier reasoning on 8GB+ GPUs
Qwen 3 Embedding 8B
permissively-licensed embeddings at 8B
Qwen 3 8B
consumer-tier reasoning toggle
Granite 3 MoE (3B active)
consumer-tier enterprise MoE
Llama 3.3 8B Instruct
consumer-tier chat — drop-in 3.1 8B replacement
Llama 3.1 Nemotron Nano 8B
consumer-tier Nemotron-Llama
DeepSeek R1 Distill Mistral 24B
consumer-tier reasoning with Mistral instruction lineage
Granite 3.2 8B
enterprise tool-calling on IBM stacks
Mistral Saba 24B
Arabic / South-Asian multilingual
Mistral Small 3 24B
consumer-tier multilingual instruction-following — Mistral's instruction-tuned baseline at 24B
Dolphin 3.0 Mistral 24B
consumer-tier creative / less-restricted generation
DeepSeek R1 Distill Qwen 14B
consumer-tier reasoning at 14B
DeepSeek R1 Distill Llama 8B
consumer-tier reasoning on 8GB+ GPUs
Falcon 3 10B
Arabic-language workloads
Falcon 3 7B Instruct
consumer-tier multilingual
Phi-4 14B
16 GB VRAM tier reasoning + chat — the right pick when 32B-class doesn't fit
OLMo 2 13B
reproducibility / academic research
Tulu 3 8B
fully-open instruction-following research baseline
Qwen 2.5 Coder 7B Instruct
consumer-tier coding at 8GB VRAM
OpenCoder 8B
academic / reproducibility-sensitive coding research
Baichuan 4 13B
Chinese-language consumer workloads — alternative to GLM
Granite 3.0 8B Instruct
enterprise-friendly Apache 2.0 baseline
Ministral 8B Instruct
consumer-tier long-context — research only
Qwen 2.5 14B Instruct
16GB-VRAM general chat with multilingual depth
Qwen 2.5 Math 7B
consumer-tier math problem solving
NV-Embed v2
research-grade embeddings
Falcon Mamba 7B
long-context inference where memory matters
Codestral Mamba 7B
long-context coding workloads where memory matters
InternLM 2.5 7B Chat
permissively-licensed long-context chat
GLM-4 9B
Chinese tool-calling agents
Aya 23 8B
multilingual research at consumer tier
CodeQwen 1.5 7B
historical reference — Qwen 2.5 Coder 7B is the modern pick
Stable LM 2 12B
12B-class deployments tolerating Stability membership
StarCoder 2 15B
permissively-licensed coding at 16GB-VRAM
StarCoder 2 7B
consumer-tier code completion at 8GB
DeepSeek MoE 16B Base
research / lineage reference
Going deeper
- Ecosystem maps — structured-landscape views (memory frameworks, inference runtimes, MCP, coding agents).
- Execution stacks — recipes that combine models with runtimes + hardware.
- Frontier index — broader ecosystem-momentum view across coding agents, inference runtimes, memory systems, MCP.
- Benchmarks — measured tokens-per-second + topology fields across hardware/model/runtime triples.