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.
Qwen3.8-27B-MLX-6bitgemma-4-E4B-it-MLX-6bitQwen3.6-27B-MLX-6bitgemma-4-12B-it-MLX-6bitQwen3.6-35B-A3B-MLX-6bitOrnith-1.5-9B-MLX-6bitgemma-4-E2B-it-MLX-6bitGLM-4.7-Flash-MLX-6bitOrnith-1.5-35B-A3B-MLX-6bitgemma-4-26B-A4B-it-MLX-6bitgemma-4-31B-it-MLX-6bitQwen3-Coder-30B-A3B-Instruct-MLX-6bitQwen3-Coder-Next-MLX-6bitQwen3-VL-4B-Instruct-MLX-6bitGLM-4.6V-Flash-MLX-6bitQwen3-VL-8B-Instruct-MLX-6bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitHermes-4-70B-MLX-6bitQwen3-4B-Instruct-2507-MLX-6bitQwen3-4B-Thinking-2507-MLX-6bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitgemma-3n-E4B-it-MLX-6bitQwen3-VL-30B-A3B-Instruct-MLX-6bitSeed-OSS-36B-Instruct-MLX-6bitQwen3-30B-A3B-Instruct-2507-MLX-6bitOlmo-3-32B-Think-MLX-6bitMistral-Small-3.2-24B-Instruct-2506-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitMagistral-Small-2509-MLX-6bit
