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.
Muse-12B-mlx-3BitMuse-12B-mlx-2BitQwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-8BitQwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-6BitQwen3-4B-Qwen3.6-plus-Reasoning-Distilled-mlx-4BitMistral-7B-UA-Grammar-GRPO-mlx-3Bitape-fiction-gemma-3-4b-mlx-8BitQwen3-4B-Qwen3.6-plus-Reasoning-Distilledape-fiction-gemma-3-4b-mlx-4BitMistral-7B-UA-Grammar-GRPO-mlx-4Bitgpt-neox-20b-mlx-4BitHuihui-HY-MT1.5-1.8B-abliterated-mlx-8BitGenBook-Deepseek-R1.Llama-8B-Q6-mlxHuihui-HY-MT1.5-7B-abliterated-mlx-5BitHuihui-HY-MT1.5-1.8B-abliterated-mlx-5Bitmaya1-mlx-4BitHuihui-HY-MT1.5-7B-abliterated-mlx-8Bitmaya1-mlx-8BitGenBook-Deepseek-R1.Llama-8B-Q4-mlxGenBook-Deepseek-R1.Llama-8B-Q3-mlxHuihui-HY-MT1.5-1.8B-abliterated-mlx-4BitCrow-9B-HERETIC-4.6-mlx-3BitLlasa-1B-Multilingual-mlx-8BitCrow-9B-HERETIC-4.6-mlx-2BitHuihui-HY-MT1.5-7B-abliterated-mlx-4BitQwQ-R1-Distill-7B-CoT-mlx-2Bitnhero2nhero3QwQ-R1-Distill-7B-CoT-mlx-4BitLlasa-1B-Multilingual-mlx-4Bit
