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.
Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-2Bitqwen2.5-coder-32b-bitnet-1.58bMistral-Small-4-119B-2603-OptiQ-2bitHuihui-MiniCPM5-1B-abliterated-mlx-2Bitqwen2.5-coder-14b-bitnet-1.58bGLM-4.7-PRISM-mlx-2BitNVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bitKimi-K2-Instruct-0905-MLX-2bitQwen3.6-27B-V2-abliterated-uncensored-6-bit-mlxgranite-4.2-8b-2bit-mlxgranite-4.2-30b-2bit-mlxLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2Bitgranite-4.2-3b-2bit-mlxQwen3.5-9B-BitClass2-GGUFgranite-4.2-8b-2bit-gptq-mlxQwen3.6-27B-V2-abliterated-uncensored-8-bit-GGUFQwen3.6-27B-V2-abliterated-uncensored-8-bit-mlxHuihui-LFM2.5-8B-A1B-abliterated-mlx-2BitQwen3.6-27B-V2-abliterated-uncensored-6-bit-GGUFMindLLM-1b3-chat-zh-v2.0Mistral-Small-24B-Instruct-2501-abliterated-4-bitERNIE-4.5-300B-A47B-2Bits-PaddleMistral-Small-24B-Instruct-2501-abliterated-8-bitQwen3-4B-Instruct-2507-BitClass3-GGUFQwen3-4B-Instruct-2507-BitClass2-GGUFGLM-4.5-Air-2bitMiniCPM5-1B-mlx-2Bitgranite-4.2-3b-2bit-gptq-mlxERNIE-4.5-300B-A47B-2Bits-TP2-PaddleMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-2Bit
