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 (42)
Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.
Muse Glimmer 30B
MiniMax-M3
Open-weight 1M-context multimodal MoE for agentic coding + video understanding
Llama 4 Maverick
frontier-tier multimodal serving on multi-machine clusters
Gemma 4 31B Dense
workstation-tier multilingual chat with permissive license
Gemma 4 26B MoE
Gemma 4 MoE — workstation efficiency variant
Gemma 4 12B
multimodal general assistant on 12-16GB GPUs
Gemma 4 E4B (Effective 4B)
edge-tier Gemma 4 — laptop friendly
Gemma 4 E2B (Effective 2B)
phone-tier Gemma 4
Qwen3.5 9B
multilingual chat and coding on 8-12GB GPUs
Phi-4 Multimodal
16GB-consumer multimodal Q&A
MiniCPM-V 3 8B
consumer multimodal document Q&A
MedGemma 27B
medical-domain fine-tune of Gemma 3 27B
Gemma 3 27B
Google's open-weight workstation-tier multilingual flagship — pre-Gemma-4 baseline
Gemma 3 12B
consumer-tier multilingual chat with vision support in 'it' variant
Gemma 3 4B
edge-tier chat — Apple Silicon laptop friendly
Qwen 2.5-VL 72B
frontier-tier multimodal serving
Qwen 2.5-VL 7B
consumer-tier OCR + image Q&A
Janus-Pro 7B
consumer multimodal with image-generation
Qwen 2.5-VL 3B
edge-tier multimodal
InternVL 2.5 78B
datacenter-tier permissive VLM
InternVL 2.5 26B
permissively-licensed VLM at 24GB VRAM
PaliGemma 2 10B
VLM fine-tuning at 24GB VRAM
PaliGemma 2 3B
task-specific VLM fine-tuning base
Whisper Large v3 Turbo
real-time / batch transcription
Llama 3.2 90B Vision
datacenter-tier multimodal serving
Llama 3.2 90B Vision Instruct
datacenter vision-language Llama at 70B-class
Molmo 72B
datacenter-tier open VLM for agent UI
Llama 3.2 11B Vision Instruct
consumer-tier vision-language Llama
Llama 3.2 11B Vision
consumer-tier multimodal — Llama-ecosystem migration path for vision workflows
Molmo 7B-D
open-research VLM with UI grounding
Pixtral 12B
consumer-tier vision-language Mistral
MiniCPM-V 2.6 8B
consumer multimodal document Q&A
Qwen 2-VL 7B
consumer-tier multimodal — pre-2.5-VL baseline
Phi-3.5 Vision
edge-tier vision-language Phi
LLaVA-OneVision 7B
permissively-licensed multi-image / video VLM
Moondream 2
edge / phone-tier vision Q&A
GLM-4V 9B
Chinese document VLM
LLaVA 1.6 Mistral 7B
consumer-tier vision-language with permissive license
Whisper Large v3
open speech-to-text baseline
Nemotron 3 Nano Omni 33B
multimodal video/audio/image/text tasks on 32GB+ GPUs
Ministral 3 14B
general chat with vision on 16GB GPUs
Trendyol LLM Asure 12B
Turkish business workflow assistants
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.