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-4.5-Air-3bitMistral-Small-4-119B-2603-Mixed-3bit-MLXgranite-4.2-8b-3bit-mlxKimi-K2-Instruct-0905-MLX-3bitQwen3.6-35B-A3B-3bit-MLXgranite-4.2-30b-3bit-mlxQwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-3bitHuihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bitgranite-4.2-3b-3bit-mlxQwen3.8-27B-3bit-mlxHuihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit-split-mtpMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit-rk3588-1.1.2Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-3bit-mixed_3_6unsloth-GLM-4.5-MLX-3Bitunsloth-GLM-4.7-mlx-3BitDevstral-Small-2505-3bitQwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-3bitQwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit-mlx-3BitQwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-3bit-mixed_3_6Qwen3-VL-235B-A22B-Instruct-Abliterated-3bitGLM-4.7-Flash-3bitGLM-4.5-Air-3bit-DWQ-v2Mistral-Small-24B-Instruct-2501-3bitgranite-4.2-8b-3bit-awq-mlxgemma-4-12B-it-3bit-mlxc4ai-command-r7b-12-2024-3bitaya-expanse-32b-abliterated-mlx-3BitMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3BitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-3BitSmolLM3-3B-3bit
