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-R1-0528-Qwen3-8B-MLX-4bitDeepSeek-R1-0528-Qwen3-8B-MLX-8bitGLM-4.7-Flash-MLX-8bitGLM-4.7-Flash-MLX-6bitQwen3-Coder-30B-A3B-Instruct-MLX-4bitQwen3-Coder-30B-A3B-Instruct-MLX-5bitQwen3-Coder-30B-A3B-Instruct-MLX-8bitQwen3-Coder-30B-A3B-Instruct-MLX-6bitQwen2.5-Coder-14B-Instruct-MLX-4bitQwen3-Coder-30B-A3B-Instruct-GGUFLFM2-24B-A2B-MLX-4bitLFM2-24B-A2B-MLX-5bitLFM2-24B-A2B-MLX-8bitLFM2-24B-A2B-MLX-6bitLFM2.5-1.2B-Instruct-MLX-8bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2.5-1.2B-Instruct-MLX-6bitQwen2.5-Coder-14B-Instruct-MLX-8bitQwen3-14B-MLX-4bitMeta-Llama-3.1-8B-Instruct-GGUFgemma-3-1b-it-GGUFQwen3-14B-MLX-8bitLlama-3.2-3B-Instruct-GGUFQwen3-8B-MLX-4bitQwen3-8B-MLX-8bitQwen3-4B-Instruct-2507-GGUFDeepSeek-R1-0528-Qwen3-8B-GGUFQwen2.5-Coder-32B-Instruct-MLX-4bitQwen2.5-Coder-32B-Instruct-MLX-8bitQwen3-32B-MLX-4bit
