Qwen/Qwen3.6-27B
Image-Text-to-Text • 28B • Updated • 5.26M • • 1.85k
Local-first LLMs
Small, capable models I run locally on a single RTX 3090 (Ollama / llama.cpp / transformers) — the backbone of self-hosted, sovereign AI.
-
-
Qwen/Qwen3.5-4B
Image-Text-to-Text • 5B • Updated • 8.4M • • 702 -
google/gemma-4-12B-it
Any-to-Any • 12B • Updated • 2.62M • 1.22k -
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 1.75M • • 1.14k -
Qwen/Qwen3-Embedding-0.6B
Feature Extraction • 0.6B • Updated • 10.1M • • 1.09k -
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
Text Generation • 12B • Updated • 575k • 2.52k -
deepreinforce-ai/Ornith-1.0-9B
Text Generation • 1.47M • Updated • 26.2k • • 304