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.
LFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitgranite-4.2-8b-MLX-6bitLFM2.5-VL-1.6B-MLX-6bitgranite-4.2-30b-MLX-6bitLlama-3.3-70B-Instruct-6bitgranite-4.2-3b-MLX-6bitSEX_ROLEPLAY-3.2-1B-mlx-6BitSmolLM3-3B-MLX-6bitLlama-4-Scout-17B-16E-Instruct-6bitEuroLLM-22B-Instruct-2512-mlx-6bitLlama-4-Maverick-17B-128E-Instruct-6bitPhi-4-mini-instruct-mlx-6BitGLM-OCR-6bitHuihui-EXAONE-4.0-32B-abliterated-mlx-6BitMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-6BitXORTRON.CriminalComputing.LARGE.2026.3-mlx-6BitLFM2.5-VL-1.6B-6bitHuihui-LFM2.5-8B-A1B-abliterated-mlx-6BitLlama-4-Scout-17B-16E-6bitc4ai-command-r7b-12-2024-6bitc4ai-command-a-03-2025-6bitMagistral-Small-2507-MLX-6bitHY-MT1.5-1.8B-6bitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-6Bitaquif-3.5-Max-42B-A3B-mlx-6BitQwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-6BitHY-MT1.5-7B-6bitBaguettotron-mlx-6Bit
