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-4bitPhi-3.5-mini-instruct-bnb-4bitPhi-4-mini-instruct-unsloth-bnb-4bitMLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bitQwen3-VL-Embedding-2B-AWQ-4bitPhi-4-mini-instruct-4bitMiLMMT-46-4B-v1.0-4bit-MLXPhi-4-mini-instruct-bnb-4bitsarvam-30b-AWQ-4bitPhi-3.5-mini-instruct-4bitHy-MT2-1.8B-4bitQwen3.8-27B-4bit-MLX-TextOnlyKimi-VL-A3B-Thinking-4bitHy-MT2-7B-4bitbge-m3-mlx-4bitVoxCPM2-4bitInternVL3_5-38B-AWQ-4bitQwen3-VL-Embedding-8B-AWQ-4bitOrnith-1.5-35B-A3B-4bit-MLXPaddleOCR-VL-1.5-4bitQwen3.8-27B-MLX-4bit-DWQPhi-3.5-mini-instruct-mlx-4BitOcten-Embedding-4B-MLX-4bitBielik-Minitron-7B-v3.0-Instruct-mlx-4BitApertus-v1.5-8B-text-MLX-4bit-DWQQwen3.5-9B-DeepSeek-V4-Flash-4bit-GGUFQwen3.6-27B-Uncensored-Heretic-v2-MLX-4bit
