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-6bitQwen3.6-27B-MLX-6bitgemma-4-E2B-it-MLX-6bitgemma-4-26B-A4B-it-MLX-6bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitQwen3-4B-Instruct-2507-MLX-6bitQwen3-4B-Thinking-2507-MLX-6bitQwen3-30B-A3B-Instruct-2507-MLX-6bitMistral-Small-3.2-24B-Instruct-2506-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitMagistral-Small-2509-MLX-6bitDevstral-Small-2507-MLX-6bitMiniMax-M2.5-MLX-6bitQwen3.5-2B-6bitMiniMax-M2-MLX-6bitcohere-transcribe-03-2026-CoreML-6bitQwen3-235B-A22B-Instruct-2507-MLX-6bitQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-mlx-6BitQwen-Image-2512-6bitQwen3.8-27B-Uncensored-OrcaRouter-MLX-6bitQwen3.8-27B-Uncensored-mlx-6BitQwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTPLX-6bitQwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bitLFM2.5-VL-450M-6bitHuihui-Qwen3.8-27B-abliterated-mlx-6BitQwen3.6-27B-AWQ-6BitQwen3.8-27B-MLX-6bitDeepSeek-OCR-2-6bitQwen3.8-27B-Heretic-Abliterated-MLX-6bit
