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 (15)
Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.
Ring-2.6-1T
frontier reasoning at MoE serving cost
Qwen 3.5 235B-A17B (MoE)
frontier-tier reasoning + multilingual serving on multi-machine clusters
Mistral Medium 3.5 (675B MoE)
frontier MoE — Mistral's response to the open MoE wave
DeepSeek V4 Pro (1.6T MoE)
frontier-tier coding + reasoning serving — currently the open-weight ceiling
DeepSeek V4
frontier-tier reasoning on multi-machine clusters
Kimi K2.6
Moonshot frontier MoE — long-context specialist
Llama 4 405B
frontier-tier serving on cluster hardware
GLM-5
Zhipu GLM-5 frontier MoE
Step-3
frontier-research workloads
Qwen 3 235B-A22B
Qwen 3 MoE flagship — pre-3.5 baseline
Llama 3.1 Nemotron Ultra 253B
frontier-tier Nemotron-Llama
DeepSeek R1 (671B reasoning)
frontier-tier reasoning research; cluster-only deployment
DeepSeek V3 (671B MoE)
frontier-tier MoE serving — pre-V4 baseline
Hunyuan Large 389B MoE
frontier-tier serving with Tencent license tolerance
Jamba 1.5 Large
frontier-tier long-context
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.