A community org for MLX model weights that run on Apple Silicon. This organization hosts ready-to-use models compatible with: - mlx-lm - A Python package for LLM text generation and fine-tuning with MLX.
Hugging Face 登录信息中包含此组织的 Pirate Face 账户。成员每次登录时更新。
Qwen3.8-27B-mxfp4Qwen3.8-27B-MTP-4bitQwen3.8-27B-4bitQwen3.8-27B-OBLITERATED-OptiQ-4bitQwen3.5-4B-OptiQ-4bitOrnith-1.5-35B-A3B-OptiQ-4bit-REAP-19BQwen3.5-9B-OptiQ-4bitUnlimited-OCR-2-8bitSpark-X2.6-4B-OptiQ-4bitMing-3.0-tts-0.5B-bf16Ming-3.0-tts-0.5B-8bitflint-mixed-3-4bitDeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtpDeepSeek-V4.1-Flash-1017-oQ2.5e-mtpDeepSeek-V4.1-Flash-1017-oQ4e-mtpMiniCPM-V-4.7-35B-A3B-mxfp4clef-omni-4bitclef-4bitclef-flash-4bitclef-8bitclef-flash-8bitembeddinggemma-2-bf16MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bitQwen-Image-2.1-mflux-q4Xing4.0-29B-A4B-OptiQ-4bithumanizer-1B-OptiQ-4bitMiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-OptiQ-4bitMiniCPM5-2B-mlx-4BitMiniCPM5-1B-mlx-6BitMiniCPM5-2B-8bitMOSS-TTS-Local-Transformer-v1.5-bf16Audio8-TTS-Preview-0.6b-bf16chatterbox-multilingual-v3Unlimited-OCR-4bitMiniCPM5-1B-OptiQ-4bitQwen3-Embedding-0.6B-8bitgemma-4-e4b-it-4bitgemma-4-e2b-it-4bitMOSS-Music-8B-Thinking-8bitmel-roformer-mlxgemma-4-12b-coder-fable5-composer2.5-4bitQwen3.6-27B-OBLITERATED-MLX-4bitsiglip2-so400m-patch16-384RIFE-4.25gemma-4-26B-A4B-it-qat-assistant-4bitCocktail-Fork-MRXCocktail-Fork-MRX-adapted-eqCocktail-Fork-MRX-adapted-loudnessCocktail-Fork-MRX-paperMuseTalk-1.5-fp16