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.
GLM-4.7-Flash-MLX-6bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-6bitERNIE-4.5-21B-A3B-MLX-6bitGLM-5.3-Flash-GGUFDeepSeek-V4-Pro-0813-GGUFGLM-4.7-Flash-6bitHy4-preview-GGUFQwen3-Coder-Next-GPTQQwen3-4B-GGUFGLM-4.7-6bitQwen3-8B-GGUFQwen3.8-Flash-Next-GGUFQwen3-30B-A3B-GGUFQwopus3.6-27B-Coder-mlx-6BitQwen3-14B-GGUFgranite-4.2-8b-MLX-6bitMiniCPM5-1B-mlx-6BitMistral-Small-4-119B-A6B-JANG_2LDeepSeek-V4-Flash-0731-GGUFLFM2.5-1.2B-Thinking-6bitNex-N2.5-mini-MLX-6bitLongCat-Flash-Lite-Sparse-6bitQwen3.8-27B-Uncensored-exl3-6bpwMiMo-V2.5-Pro-6bitAgnes-3.0-Flash-MLX-6bit-MTPLFM2.5-2.6B-MLX-6bitQwen3-Coder-Next-AWQgranite-4.2-30b-MLX-6bitGLM-4.5-Air-MLX-6bit
