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.
ruby3.4-llama-3.1-8b-5k-all-16bit-geminiruby3.4-gemma-2-9b-1k-all-16bit-geminiruby3.4-llama-3.1-8b-5k-hq-8bit-geminiruby3.4-qwen2.5-7b-instruct-5k-hq-4bit-geminiruby3.4-qwen2.5-7b-instruct-1k-all-8bit-geminiruby3.4-qwen2.5-7b-instruct-5k-all-8bit-geminiruby3.4-qwen2.5-7b-instruct-1k-hq-16bit-geminiruby3.4-qwen2.5-7b-instruct-5k-all-16bit-geminiruby3.4-qwen2.5-7b-instruct-5k-hq-16bit-geminiruby3.4-qwen2.5-coder-1.5b-1k-hq-8bit-geminiruby3.4-qwen2.5-7b-instruct-1k-all-4bit-geminiruby3.4-qwen2.5-coder-1.5b-5k-all-8bit-geminiruby3.4-qwen2.5-7b-instruct-1k-hq-4bit-geminiruby3.4-qwen2.5-7b-instruct-5k-all-4bit-geminiruby3.4-qwen2.5-7b-instruct-1k-all-16bit-geminigem-rubyruby3.4-qwen2.5-coder-1.5b-5k-hq-8bit-geminiruby3.4-qwen2.5-7b-instruct-5k-hq-8bit-geminiruby3.4-qwen2.5-coder-7b-1k-all-16bit-geminiruby3.4-gemma-2-9b-5k-all-16bit-geminiruby3.4-llama-3.1-8b-1k-hq-8bit-geminiruby3.4-qwen2.5-7b-instruct-1k-hq-8bit-geminiruby3.4-gemma-2-9b-5k-hq-8bit-geminiruby3.4-llama-3.1-8b-1k-all-16bit-geminiruby3.4-llama-3.1-8b-1k-hq-16bit-geminiruby3.4-gemma-2-2b-1k-all-8bit-geminiruby3.4-llama-3.2-3b-5k-all-8bit-geminiruby3.4-llama-3.1-8b-1k-hq-4bit-geminiruby3.4-qwen2.5-coder-7b-1k-all-4bit-geminiruby3.4-qwen2.5-coder-7b-5k-all-8bit-gemini