models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen2.5-VL-7B-Instruct-4bitLlama-3.2-11B-Vision-Instruct-4bitHuihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bitQwen3-Coder-30B-A3B-Instruct-4bitDeepSeek-R1-Distill-Qwen-14B-4bitdeepseek-coder-33b-instruct-hf-4bit-mlxDeepSeek-R1-Distill-Qwen-32B-4bitQwen2.5-Coder-1.5B-Instruct-4bitLlama-3.3-70B-Instruct-4bitQwen2.5-Coder-7B-Instruct-4bitMistral-Small-24B-Instruct-2501-4bitGLM-4.5-Air-4bitQwen2.5-Math-7B-Instruct-4bitgpt-oss-20b-MXFP4-Q4DeepSeek-R1-Distill-Qwen-7B-4bitMistral-Small-3.1-24B-Instruct-2503-4bitDevstral-Small-2507-4bit-DWQgemma-4-e4b-it-4bitgemma-4-26b-a4b-it-4bitQwen3-14B-4bitgpt-oss-120b-4bitgemma-3-1b-it-4bitPhi-4-mini-instruct-4bitgemma-4-31b-it-4bitgemma-3-text-4b-it-4bitVibeThinker-1.5B-mlx-4bitPhi-4-reasoning-plus-4bitQwen3.5-27B-4bitmem-agent-mlx-4bitQwen2.5-0.5B-Instruct-GGUF
