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.
qwen3-tts-0-6b-custom-voice-mix-precisionQwen3.8-27B-AEON-Ultimate-Uncensored-Multimodal-MLX-6bitDeepSeek-OCR-2-6bitnemotron-3.5-asr-offline-6bit-CoreMLQwen3.6-35B-A3B-Uncensored-Heretic-MLX-6bitqwen3-tts-0-6b-base-mix-precisionQwen3.8-27B-6bit-MLX-TextOnlyApertus-v1.5-8B-text-MLX-6bitOrnith-1.5-35B-A3B-6bit-MLX-TextOnlybge-m3-mlx-6bitKimi-VL-A3B-Thinking-6bitOrnith-1.5-35B-A3B-6bit-MLXPhi-4-mini-instruct-6bitQwen3.6-27B-Uncensored-Heretic-v2-MLX-6bitPaddleOCR-VL-1.6-6bitInternVL3-8B-6bitKAT-Dev-MLX-6bitparakeet-tdt-0-6b-v3-int8-litertDeepSeek-OCR-6bitQwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-6bit-mlxQwen3.8-27B-6bit-MLXUnlimited-OCR-6bitzembed-1-embedding-mlx-6BitHunyuan-MT2-1.8B-6bit-MLXApertus-v1.5-8B-MLX-6bitInternVL3-14B-6bitdots.ocr-6bitInternVL3-38B-6bitInternVL3-9B-6bitPhi-4-mini-instruct-mlx-6Bit
