Frontier zone · Model releases

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.

By Eruo Fredoline · Refreshed continuously from catalog seed

Filter

Family

Any Qwen Llama DeepSeek Mistral Gemma Phi GLM OLMo

Deployment

Any Edge Consumer Workstation Datacenter Frontier

Modality

Any Multimodal Text-only

Coverage

Any L1.25 enriched Needs L1.25 Needs benchmark

Filtered results (4)

Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.

Muse Glimmer 30B

Meta · 2026-08-10

30Bworkstation

BenchmarkVerdictMultimodal

Gemma 4 26B MoE

Google · 2026-04-02

26Bworkstation

Gemma 4 MoE — workstation efficiency variant

VerdictMultimodal

MedGemma 27B

Google · 2025-05-20

27Bworkstation

medical-domain fine-tune of Gemma 3 27B

VerdictMultimodal

Nemotron 3 Nano Omni 33B

NVIDIA

33Bworkstation

multimodal video/audio/image/text tasks on 32GB+ GPUs

BenchmarkMultimodal

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.