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.
Qwen3.8-9B-mlx-3BitLlama-3.3-70B-Instruct-3bitGLM-4.5-Air-3bitQwen3.8-2.4T-A95B-3bit-UVMAXLongCat-2.0-3bitLongCat-2.0-3bit-UVMAXKimi-K2-Instruct-0905-MLX-3bitHuihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3BitQwen3.8-27B-DynQuant-3bitQwen2.5-Coder-32B-Instruct-3bitQwen3.8-32B-Jumbo-3bitQwen2.5-Coder-7B-Instruct-3bitQwen3.5-35B-A3B-DynQuant-3bitHuihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3Bit-split-mtpMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit-rk3588-1.1.2Devstral-Small-2-24B-Instruct-2512-MLX-3bitgranite-4.2-30b-3bit-mlxHunyuan-A52B-Instruct-3bitQwen3.8-4B-mlx-3BitQwen3.8-2B-mlx-3BitQwen2.5-Coder-32B-Instruct-abliterated-3bitMuse-12B-mlx-3Bitgranite-4.2-3b-3bit-mlxgranite-4.2-8b-3bit-mlxTinytron-ORCA-3B-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bitzeta-2.1-3bitunsloth-GLM-4.5-MLX-3Bitunsloth-GLM-4.7-mlx-3BitDevstral-Small-2505-3bitEXAONE-3.5-7.8B-Instruct-3bit