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.
Qwen2.5-3B-Instruct-bnb-4bitdeepseek-r1-0528-distilled-qwen3-ggufLlama-3.2-1B-Instruct-bnb-4bitqwen3-1.7b-mixed-thoughtQwen2.5-1.5B-Instruct-bnb-4bitGranite-4.1-3b-coderQwen3-4b-tcomanr-merge-v2.3Qwen3-4b-tcomanr-merge-v2.5Phi-4-mini-instruct-bnb-4bitQwen2.5-0.5B-Instruct-bnb-4bitLFM2.5-230Mdeepseek-v4-distill-qwen3-1.7bLlama-3.2-1B-Instructqwen3-4b-code-reasoning-v2LFM2.5-1.2B-InstructQwen2.5-1.5B-InstructQwen3-4B-distill-deepseek-opus-geminiqwen3-4b-claude-sonnet-x-gemini-reasoningLFM2.5-350Mqwen3-4b-instruct-human-like-dpoQwen3-4b-2507-Thinking-math-and-codeQwen3-4B-distill-deepseek-opus-gemini-ethical-trainingLlama-3.2-3B-Instruct-bnb-4bitPhi-4-mini-instructQwen3-1.7B-tiny-orchestratordeepseek-r1-0528-distilled-qwen3Qwen3-4b-thinking-gpt5.1-distillQwen2.5-0.5B-InstructLlama-3.2-3B-InstructQwen2.5-3B-Instruct
