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.
phi-2-llamafileMeta-Llama-3-8B-Instruct-llamafileMistral-7B-Instruct-v0.2-llamafilePhi-3-mini-4k-instruct-llamafileTriLM-llamafileQwen3-30B-A3B-llamafileMeta-Llama-3-70B-Instruct-llamafileQwen3-4B-llamafileTinyLlama-1.1B-Chat-v1.0-llamafileQwen2.5-3B-Instruct-GGUF-llamafilegranite-34b-code-instruct-llamafileQwen3.8-27B-llamafileTinyLLama-v0-5M-F16-llamafileQwen2.5-32B-Instruct-GGUF-llamafileQwen3.8-27B-Heretic-ARA-Uncensored-llamafileOpenHermes-2.5-Mistral-7B-llamafileQwen2.5-Coder-1.5B-Instruct-GGUF-llamafilegemma-3-4b-it-llamafileqwen-llamafilesDeepSeek-R1-Distill-Qwen-7B-llamafileQwen2.5-Coder-7B-Instruct-GGUF-llamafilegemma-3-1b-it-llamafileQwen3.8-27B-OrcaRouter-Uncensored-llamafileQwen2.5-0.5B-Instruct-GGUF-llamafileQwen2.5-7B-Instruct-GGUF-llamafilegemma-3-12b-it-llamafileQwen3.8-27B-Ultra-Heretic-Uncensored-llamafileQwen2.5-Coder-14B-Instruct-GGUF-llamafileQwen2.5-0.5B-Instruct-llamafileQwen2.5.1-Coder-7B-Instruct-llamafile