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-GPTQ-W4A8-MTP-AmpereQwen3.8-27B-MTP-W4A16-VOLTA-AmpereDeepSeek-v4-flash-180b-W4A16-VOLTA-AmpereQwen3-VL-4B-Instruct-GGUFQwen3-VL-8B-Instruct-GGUFgemma-4-E4B-it-Ampereqwen-2.5-vl-3b-instruct-ggufqwen-2.5-vl-7b-instruct-ggufllama-3.2-1b-instruct-ggufgemma-3-27b-it-ggufqwen-3-a3b-30b-ggufqwen-3-a22b-235b-ggufbge-m3-ggufdeepseek-r1-0528-ggufllama-3.2-3b-instruct-ggufllama-4-scout-16e-17b-instruct-ggufgemma-3-4b-it-ggufdeepseek-v3.1-ggufllama-3.1-8b-ggufqwen-3-8b-ggufqwen-3-coder-a3b-30b-instruct-ggufQwen3-VL-2B-Instruct-GGUFqwen-2.5-0.5b-instruct-ggufgemma-3-12b-it-ggufgranite-3.3-8b-instruct-ggufllama-3.1-8b-instruct-ggufbielik-v3.0-4.5b-instruct-ggufqwen-2.5-3b-instruct-ggufqwen-3-14b-ggufqwen-2.5-14b-instruct-gguf
