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.
Ternary-Bonsai-27B-mlx-2bitTernary-Bonsai-2-27B-mlx-2bitbitnet-b1.58-2B-4Tbitnet-b1.58-2B-4T-ggufTernary-Bonsai-8B-mlx-2bitDeepSeek-V4-Flash-2bit-DQDeepSeek-V4.1-Flash-MLX-2bit-MTPbitnet-b1.58-2B-4T-bf16Dirty-Muse-Writer-v01-Uncensored-Erotica-NSFW-mlx-2BitDeepSeek-V4.1-Flash-REAP-2bit-MLXDeepSeek-V4-Flash-0731-OptiQ-2bit2-bit-LLMsTernary-Bonsai-2-27B-mlx-2bitQwen3.8-27B-2bit-MLX-TextOnlyTernary-Bonsai-1.7B-mlx-2bitKimi-K3-mlx-reap160-2bitMistral-Small-4-119B-2603-OptiQ-2bitTernary-Bonsai-4B-mlx-2bitTernary-Bonsai-2-27B-mlx-2bitQwen3.8-Flash-Next-OptiQ-2bitishaanxgupta-gemma-2-2bit-quantised-GGUFQwen3-8B-BPDQ-2bitqwen2.5-coder-32b-bitnet-1.58bQwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-2BitHuihui-MiniCPM5-1B-abliterated-mlx-2BitTernary-Bonsai-2-27B-mlx-2bitQwen3.6-35B-A3B-RotorQuant-MLX-2bitQwen3.8-27B-2bitHy3-OptiQ-2bitNVIDIA-Nemotron-3-Super-120B-A12B-OptiQ-2bit
