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.
gemma-4-26B-A4B-it-qat-OptiQ-4bitgpt-oss-20b-OptiQ-4bitQwen3.5-9B-OptiQ-4bitQwen3.8-27B-Uncensored-OptiQ-4bitQwen3.5-4B-OptiQ-4bitQwen3.6-35B-A3B-OptiQ-4bit-REAP-19Bgemma-4-12B-it-qat-OptiQ-4bitQwen3.6-35B-A3B-OptiQ-4bitOrnith-1.5-9B-OptiQ-4bitDeepSeek-V4-Flash-0731-OptiQ-2bitMiniCPM5-1B-OptiQ-4bitOrnith-1.5-35B-A3B-OptiQ-4bit-REAP-19Bgemma-4-12B-it-OptiQ-4bitQwen3.6-27B-OptiQ-4bitMiMo-V2.6-Distill-Qwen-9B-OptiQ-4bitgemma-4-e4b-it-qat-OptiQ-4bitMiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-OptiQ-4bitQwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-3.7bpw-mlxSpark-X2.5-4B-OptiQ-4bitMiniCPM5-2B-OptiQ-4bitgemma-4-e4b-it-OptiQ-4bitgemma-4-26B-A4B-it-OptiQ-4bit-REAP-14BKAT-Coder-V2.5-Dev-OptiQ-4bit-REAP-18Bgemma-4-31B-it-qat-OptiQ-4bitNVIDIA-Nemotron-3.5-Lightning-30B-A3B-OptiQ-4bitQwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-6bpw-MLXKAT-Coder-V2.5-Dev-OptiQ-4bitQwen3.5-0.8B-OptiQ-4bitgemma-4-26B-A4B-it-OptiQ-4bitgemma-4-e2b-it-qat-OptiQ-4bit