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.
bitnet-b1.58-2B-4TDeepSeek-V4-Flash-2bit-DQbitnet-b1.58-2B-4T-ggufbitnet-b1.58-2B-4T-bf16Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-2Bitqwen2.5-coder-32b-bitnet-1.58bMistral-Small-4-119B-2603-OptiQ-2bitHuihui-MiniCPM5-1B-abliterated-mlx-2BitJosiefied-Qwen2.5-3B-Instruct-abliterated-v1-4-bitGLM-4.7-PRISM-mlx-2Bitqwen2.5-coder-14b-bitnet-1.58bNVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bitQwen3.8-9B-mlx-2BitKimi-K2-Instruct-0905-MLX-2bitQwen3.6-27B-V2-abliterated-uncensored-6-bit-mlxgranite-4.2-8b-2bit-mlxLongCat-2.0-2bitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-2Bitgranite-4.2-30b-2bit-mlxJosiefied-Qwen2.5-7B-Instruct-abliterated-v2-4-bitQwen3.5-27B-TurboQuant-MLX-2bitgranite-4.2-3b-2bit-mlxQwen3.5-9B-BitClass2-GGUFbitnet-b1.58-2B-4TMistral-Small-4-119B-TurboQuant-MLX-2bitgranite-4.2-8b-2bit-gptq-mlxQwen3.8-4B-mlx-2BitQwen3.6-27B-V2-abliterated-uncensored-8-bit-GGUFLLaDA2.2-flash-OptiQ-2bitQwen3.6-27B-V2-abliterated-uncensored-8-bit-mlx
