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.
Llama-3.3-70B-Instruct-3bitQwen3.5-35B-A3B-DynQuant-3bitMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bit-rk3588-1.1.2granite-4.2-30b-3bit-mlxgranite-4.2-3b-3bit-mlxgranite-4.2-8b-3bit-mlxTinytron-ORCA-3B-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bitDevstral-Small-2505-3bitTinytron-ORCA-7B-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bitMeta-Llama-3.1-8B-Instruct-3bitMeta-Llama-3.1-8B-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bitgranite-4.2-8b-3bit-awq-mlxMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-3Bitgemma-4-12B-it-3bit-mlxc4ai-command-r7b-12-2024-3bitaya-expanse-32b-abliterated-mlx-3BitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-3BitSmolLM3-3B-3bitcommand-r-plus-08-2024-3bit-mlxgranite-4.2-3b-3bit-awq-mlxc4ai-command-a-03-2025-3bitgemma-4-E4B-it-3bit-mlxexaone-4.0-32b-3bitHuihui-LFM2.5-8B-A1B-abliterated-mlx-3BitQwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-3BitSmolLM3-3B-Base-3bitgemma-4-E2B-it-3bit-mlxFalcon3-1B-Instruct-3bitLlama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-3BitTinytron-Qwen-0.5B-TinyLlama-Instruct_CODE_Python-extra_small_quantization_GGUF_3bit