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.
GLM-4.7-Flash-MLX-6bitQwen3-Coder-30B-A3B-Instruct-MLX-6bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitQwen3-4B-Instruct-2507-MLX-6bitQwen3-4B-Thinking-2507-MLX-6bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitSeed-OSS-36B-Instruct-MLX-6bitQwen3-30B-A3B-Instruct-2507-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitQwen3-Next-80B-A3B-Instruct-MLX-6bitMiniMax-M2.5-MLX-6bitMiniMax-M2-MLX-6bitQwen3-Coder-480B-A35B-Instruct-MLX-6bitQwen3-235B-A22B-Instruct-2507-MLX-6bitLlama-3.2-3B-Instruct-uncensored-6bitOrnith-1.0-9B-MLX-6bitgranite-4.2-8b-MLX-6bitMiniCPM5-1B-mlx-6BitQwen3.8-9B-mlx-6BitOrnith-1.0-35B-MLX-6bitgranite-4.2-30b-MLX-6bitLlama-3.3-70B-Instruct-6bitGLM-4.5-Air-MLX-6bitQwen3-30B-A3B-Thinking-2507-MLX-6bitQwen3.8-9B-mlx-6BitQwen2.5-Coder-32B-Instruct-6bitMLX-Qwen3.5-9B-GLM5.1-Distill-v1-6bitgranite-4.2-3b-MLX-6bitPsych_medgemma-mlx-6Bit