Models I can run locally so far
-
nvidia/Qwen3.8-2.4T-A95B-NVFP4
Text Generation • 1.3T • Updated • 3k • 24 -
mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit
Text Generation • 25B • Updated • 1.24k • 21 -
mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit
Text Generation • 35B • Updated • 3.95k • 82 -
google/gemma-3-12b-it-qat-q4_0-unquantized
Image-Text-to-Text • 12B • Updated • 7.38k • • 220