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-6bitGLM-4.6V-Flash-MLX-6bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitMistral-Small-3.2-24B-Instruct-2506-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitMagistral-Small-2509-MLX-6bitDevstral-Small-2507-MLX-6bitcohere-transcribe-03-2026-CoreML-6bitQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-6BitQwen3.8-27B-Uncensored-OrcaRouter-MLX-6bitQwen3.8-27B-Uncensored-mlx-6BitGLM-4.7-Flash-6bitQwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bitLFM2.5-VL-450M-6bitGLM-4.7-6bitgranite-4.2-8b-MLX-6bitQwopus3.6-27B-Coder-mlx-6BitQwen3.8-27B-ABLITERATED-UNCENSORED-PHILADELPHIA-CLASS-MLX-mixed-6bitQwen3.6-35B-A3B-Uncensored-Heretic-MLX-6bitLFM2.5-VL-1.6B-MLX-6bitQwen-Image-Layered-6bitLFM2.5-1.2B-Thinking-6bitMiniCPM5-1B-mlx-6Bitgranite-4.2-30b-MLX-6bitNex-N2.5-mini-MLX-6bitLongCat-Flash-Lite-Sparse-6bitLFM2.5-2.6B-MLX-6bitQwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-6bitMiMo-V2.5-Pro-6bit
