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.
LFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitLFM2.5-VL-1.6B-MLX-6bitQwen2.5-Coder-32B-Instruct-6bitzeta-2.1-6bitQwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-mlx-6BitQwen2.5-Coder-14B-Instruct-abliterated-6bitQwimi3.5-9B-Kimik2.6-Opus-Distill-MLX-6BitolmOCR-2-7B-1025-6bitQwen2.5-VL-7B-Instruct-6bitQwen2.5-Coder-14B-Instruct-mlx-6Bitall-MiniLM-L6-v2-6bitmedgemma-27b-it-heretic-mlx-6BitEuroLLM-22B-Instruct-2512-mlx-6bitQwimi-3.6-27B-Coder-MTP-mlx-6BitQwen2.5-VL-32B-Instruct-6bitQwen2.5-VL-3B-Instruct-6bitmedgemma-27b-text-heretic_med-mlx-6BitQwen3.8-2B-mlx-6BitQwen2.5-72B-Instruct-6bitSmolLM2-360M-Instruct-6bitmarvis-tts-250m-v0.2-MLX-6bitQwen2.5-14B-Instruct-1M-6bitgemma-4-26B-A4B-it-Claude-Opus-Distilled-v2-MLX-6bit-int6-affineQwen2.5-VL-72B-Instruct-6bitMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-6BitXORTRON.CriminalComputing.LARGE.2026.3-mlx-6BitDolphin3.0-R1-Mistral-24B-6bitgemma-4-31B-it-Claude-Opus-Distilled-v2-MLX-6bit-int6-affine
