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.
Mistral-Small-4-119B-2603-OptiQ-2bitNVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bitgranite-4.2-8b-2bit-mlxLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2Bitgranite-4.2-30b-2bit-mlxgranite-4.2-3b-2bit-mlxgranite-4.2-8b-2bit-gptq-mlxHuihui-LFM2.5-8B-A1B-abliterated-mlx-2Bitgranite-4.2-3b-2bit-gptq-mlxMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-2Bitgranite-4.1-8b-2bit-gptq-mlxgemma-4-12B-it-2bit-mlxgranite-4.2-8b-2bit-awq-mlxMeta-Llama-3.1-405B-2bitgranite-4.2-3b-2bit-awq-mlxc4ai-command-r-plus-2bitQwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-2Bitgemma-4-E4B-it-2bit-mlxQwopus3.6-35B-A3B-v1-MLX-2bit-mixed_2_6Qwopus3.6-27B-v2-MLX-2bit-mixed_2_6granite-4.1-3b-2bit-gptq-mlxgemma-4-E2B-it-2bit-mlxSoofi-S-Isar-Preview-EntQuant-2bitgranite-4.1-3b-2bit-awq-mlxMistral-Nemo-Instruct-2407-AQLM-PV-2Bit-1x16-hfcohere-transcribe-03-2026-MLX-Mixed-2bit3bit4bitMistral-Nemo-Instruct-2407-heretic-noslop-mlx-2BitLlama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-2Bitgranite-4.1-8b-2bit-mlxgranite-4.1-8b-2bit-awq-mlx
