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.
gemma-3-4b-it-qat-4bitgemma-3-12b-it-qat-4bitgemma-3-27b-it-qat-4bitQwen3.6-35B-A3B-Uncensored-Heretic-MLX-4bitMLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bitQwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-8BitDeepSeek-OCR-8bitQwen3.8-27B-3bit-MLXQwen3.6-35B-A3B-Uncensored-Heretic-MLX-8bitQwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-8bitQwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bitQwen3.6-27B-AEON-Ultimate-Uncensored-BF16-mlx-2BitQwen3.8-27B-AEON-ULTIMATE-UNCENSORED-BF16-mlx-8BitDeepSeek-OCR-2-6bitQwen3.8-27B-Cold-Fusion-GAIN-V1.1-Fable-mxfp8-mlxQwen3.8-27B-2bit-MLXPaddleOCR-VL-1.6-MLX-8bitQwen3.6-35B-A3B-Uncensored-Heretic-MLX-6bitKimi-VL-A3B-Thinking-4bitQwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-KAT-Coder-C-qx86-hi-mlxQwen3.8-27B-Brainwaves-1M-qx86-hi-mlxQwen3.8-27B-Fable-Fusion-F711-GAIN-mxfp4-mlxQwen3.8-27B-Brainwaves-WFH-mxfp4-mlxQwen3.5-9B-Theseus-q8-hi-mlxDeepSeek-OCR-2-bf16DeepSeek-OCR-2-8bitQwen3.8-27B-AEON-ULTIMATE-UNCENSORED-MLX-MIXED-VISION-MTPLXOrnith-1.5-35B-A3B-4bit-MLXQwen3.8-27B-Brainwaves-mxfp8-mlxPaddleOCR-VL-1.5-4bit
