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 (19)
Models matching your filters. Clear filters by clicking “Any” on each row above, or remove individual filters via the URL.
Phi-4 Multimodal
16GB-consumer multimodal Q&A
MiniCPM-V 3 8B
consumer multimodal document Q&A
Gemma 3 12B
consumer-tier multilingual chat with vision support in 'it' variant
Qwen 2.5-VL 7B
consumer-tier OCR + image Q&A
Janus-Pro 7B
consumer multimodal with image-generation
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
Llama 3.2 11B Vision
consumer-tier multimodal — Llama-ecosystem migration path for vision workflows
Llama 3.2 11B Vision Instruct
consumer-tier vision-language Llama
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
LLaVA-OneVision 7B
permissively-licensed multi-image / video VLM
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
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.