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.
DeepSeek-R1-Distill-Qwen-14B-MLX-4bitOutlier-150B-V3.2Qwen3-Coder-30B-A3B-Instruct-MLX-4bitDeepSeek-R1-Distill-Qwen-32B-MLX-4bitQwen2.5-Coder-14B-Instruct-MLX-4bitQwen2.5-Coder-32B-Instruct-MLX-4bitQwen2.5-Coder-7B-Instruct-MLX-4bitQwen3-14B-MLX-4bitDeepSeek-R1-Distill-Llama-8B-MLX-4bitDeepSeek-R1-Distill-Qwen-7B-MLX-4bitOutlier-Max-32B-GGUFOutlier-10B-V2-GGUFOutlier-Compact-14B-GGUFOutlier-Lite-7B-GGUFOutlier-Core-27B-MLX-4bitOutlier-Quick-26B-MLX-4bitOutlier-10B-V3.2Phi-4-mini-instruct-MLX-4bitQwen3-8B-MLX-4bitgemma-3-27b-it-MLX-4bitOutlier-Nano-4B-MLX-4bitQwen3-32B-MLX-4bitOutlier-10BOutlier-Nano-1.7B-MLX-4bitgemma-3-4b-it-MLX-4bitOutlier-Lite-9B-MLX-4bitOutlier-Code-27B-MLX-4bitOutlier-10B-V2Outlier-40B-V3.2Outlier-Vision-35B-A3B-MLX-4bit
