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 (26)
Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.
Llama 4 70B
production self-hosted serving on 2x A100 / H100
EVA Llama 3.3 70B
datacenter-tier creative / narrative generation
Llama 3.3 8B Instruct
consumer-tier chat — drop-in 3.1 8B replacement
Llama 3.1 Nemotron Nano 8B
consumer-tier Nemotron-Llama
Llama 3.3 70B Instruct
production self-hosted serving at the 70B class — when you need general-purpose capability above 32B but don't need frontier-tier
Llama 3.1 Nemotron 70B Instruct
NVIDIA-fine-tuned Llama 3.1 70B
Llama 3.1 70B Instruct
production self-hosted serving at the 70B class
Phind CodeLlama 34B v2
historical reference for Llama 2 coder lineage
Hermes 4 70B FP8
English/multilingual STEM reasoning and structured data extraction
ALIA 40b instruct 2601
Spanish-region enterprise document processing and multilingual Iberian assistant apps
OpenThaiGPT 1.0.0 Beta 13B Chat
Basic Thai-language instruction following and Q&A
Bielik 11B v3.0 Instruct GGUF
Polish-language instruction following and document Q&A
Bielik-11B v3.0 Instruct FP8 Dynamic
Polish-language instruction following and chat on constrained GPU hardware
SOLAR 10.7B v1.0
Foundation for custom fine-tuning pipelines
Cosmos Llama 3 8B Turkish
Saiga Llama3 8B GGUF
Russian conversational assistant on consumer hardware
LLM-jp 4 8B Instruct
Japanese/English bilingual document summarization and extraction
Gervásio 8B PTPT
European Portuguese text tasks where PT-BR is acceptable collateral
LLM-jp 4 8B Thinking
Internal Japanese-English reasoning and document processing pipelines
Turkish Llama 8B Instruct v0.1
Trendyol LLM 7B Base v0.1
Trendyol LLM 7B Chat v0.1
Salamandra 7B Instruct
Spanish and European multilingual chat prototyping
Swallow 7B
Japanese-language fine-tuning base or research
Salamandra 7B
Spanish/Catalan fine-tuning base for custom NLP pipelines
OpenThaiGPT 7B 1.0.0 Chat
Thai-language instruction-following and chat
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.