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.
Qwen3.8-27B-UD-Q3_K_XL-DFlash2-MLXQwen3.8-27B-DFlash2-Q3_K_M-GGUFQwen3.8-27B-UD-Q3_K_XL-MTP-MLXQwen3.8-27B-UD-Q3_K_XL-MLX-imatrix-directQwen3-8B-Q3_K_M-GGUFqwen3.5-9B-super-coder-Q3KM-GGUFQwen-Qwen2.5-Coder-14B-Instruct-GGUF-Q3_K_Mgemma-4-e2b-it-Q3_K_M-GGUFQwen3.8-27B-UD-Q3_K_XL-MLX-gptq-directQwen3-Coder-30B-A3B-Instruct-Q3_K_M-GGUFQwen3.6-35B-A3B-UD-Q3_K_XL-mlxgemma-2-2b-it-Q3_K_M-GGUFQwen2.5-7B-Instruct-Q3_K_M-GGUFQwen3-Coder-30B-A3B-Instruct-Q3_K_M-GGUFQwen3.8-27B-UD3-Q3_K_XL-MLXgemma-4-12B-it-RotorQuant-GGUF-Q3_K_MQwen2.5-7B-Instruct-Uncensored-Q3_K_M-GGUFGLM-5.2-REAP50-Q3_K_M-GGUFDeepSeek-R1-Distill-Qwen-7B-Q3_K_M-GGUFHuihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-Q3_K_M-GGUFQwen3.6-27B-UD-Q3_K_XL-mlxDolphin3.0-Llama3.1-8B-Q3_K_M-GGUFLLama-3-8b-Uncensored-Q3_K_M-GGUFQwen3.5-27B-RotorQuant-GGUF-Q3_K_Mgpt-oss-20b-RotorQuant-GGUF-Q3_K_MNemotron-3-Super-120B-A12B-TurboQuant-GGUF-Q3_K_MQwen2.5-Coder-14B-Instruct-Uncensored-Q3_K_M-GGUFBrahmaputra-1-GGUF-Q3_K_MQwen1.5-MoE-A2.7B-Chat-Q3_K_M-GGUFgemma-4-31b-it-Q3_K_M-GGUF