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.
Gemini-Q4_0-GGUFgemma-4-E2B-Gemini-3.1-Pro-Reasoning-Distillruby3.4-gemma-2-9b-1k-hq-16bit-geminigemma2b-summarize-gemini1_5flash-128kgemini-1.5-pro-gemma-rewrite-1024kimi-k26-o2-nohhh-v3-gemini-6k-rlaif-loragemini-all-data20240415_025230gemini-all-data20240415_051850blip2-opt-2.7b-geminipv-captions-adaptersGemma-4-12B-Gemini-3.5-flash-Reasoning-Distillruby3.4-gemma-2-9b-5k-hq-16bit-geminiqlora-gemini-persona-qna-finetunedgemma7b-summarize-gemini1.5flash-30kqwen3-8b-distilled-r64-gemini_3_flash-allgemma7b-summarize-gemini1.0pro-11kruby3.4-qwen2.5-coder-1.5b-1k-all-4bit-geminigemma2b-summarize-gemini1_5flash-32kgemma2b-summarize-gemini1_5flash-64kGeminigemma-4-E2B-Gemini-3.1-Pro-Reasoning-Distillruby3.4-qwen2.5-coder-7b-1k-all-4bit-geminiqwen3-viet-summarization-gemini-synthchandra-supervised-lora-gemini-full-5epochsbilsem-qwen3vlit-8b-gemini3pro_qwen3vlflash-110-loraruby3.4-gemma-2-2b-1k-all-4bit-geminigemma2b-summarize-gemini1_5flash-1kruby3.4-qwen2.5-7b-instruct-5k-all-8bit-geminiruby3.4-qwen2.5-7b-instruct-5k-all-16bit-geminiwar-room-grpo-adapter-smoke-v2lfm-sft-hotter-colder-gemini-simplified-reasoning-lora