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.
gpt-oss-20b-MXFP4-Q8Agents-A1-4B-Q8_0-GGUFMellum2-12B-A2.5B-Instruct-GGUF-Q8_0Nanbeige4.1-3B-Q8_0-GGUFQwen3.8-27B-Heretic-Uncensored-Q8_0-GGUFQwen3-Coder-30B-A3B-Instruct-Q8_0-GGUFQwen3-4B-Instruct-2507-Q8_0-GGUFLlama-3.2-1B-Instruct-Q8_0-GGUFKimi-K3-REAP80-MLX-mxfp4-q8Qwen2.5-Coder-1.5B-Q8_0-GGUFgpt-oss-120b-MXFP4-Q8Kimi-K3-REAP73-MLX-mxfp4-q8Qwen3.8-Flash-Next-MTP-Q8_0-GGUFQwen3-8B-Q8_0-full-v2.ggufGLM-5.2-Q2_K-MTP-Q8-layersQwen2.5-Coder-1.5B-Instruct-Q8_0-GGUFSpark-X2.5-4B-Q8_0-GGUFOneLLM-Doey-V1-Llama-3.2-1B-it-Q8_0-GGUFOneLLM-Doey-ChatQA-V1-Llama-3.2-1B-Q8_0-GGUFQwen2.5-Coder-14B-Instruct-Q8_0-GGUFQwen2.5-Coder-7B-Q8_0-GGUFQwen2.5-Coder-3B-Q8_0-GGUFQwen3.8-27B-Atlassian-Q8-mlxKimi-K2.7-Code-mlx-DQ3_K_M-q8OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlxQwen2.5-Coder-7B-Instruct-Q8_0-GGUFQwen3.8-27B-UD-Q8_K_XL-layers-v0762Llama-3.2-3B-Instruct-Q8_0-GGUFQwen3.8-27B-UD-Q8_K_XL-layersKimi-K2.6-mlx-DQ3_K_M-q8