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.
Replete-Coder-V2-Llama-3.1-8b-GGUFLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-8BitMeta-Llama-3.1-8B-Instruct_CODE_Python_English_Asistant-16bit-v2-i1-GGUFFireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-GGUFLlama-3-11.5B-Instruct-Coder-v2-GGUFcodellama-7b-bnb-4bitLlama-3-8B-Instruct-Coder-v2-GGUFMathCoder2-CodeLlama-7B-GGUFCode-Llama-3-8BLlama-3-8B-Instruct-Coder-GGUFMeta-Llama-3.1-8B-Instruct_CODE_Python_English_Asistant-16bit-v2-GGUFCode-Llama-3-8B-GGUFQwen3-4b-toolcall-gguf-llamacpp-codexSamantha-1.11-CodeLlama-34B-GGUFLlama-3-8B-Instruct-Coder-GGUFspeechless-codellama-34b-v2.0-GGUFLlama-3B-Coderqwen36-a3b-claude-coder-llama.cpp-GGUFlayerskip-codellama-7BMathCoder2-CodeLlama-7B-GGUFLlama3.2-3B-Claude-Reasoning-DistillLlama-3.1-Minitron-4B-Instruct_CODE_Python-GGUF_Spanish_English_8bitcodellama-34b-bnb-4bitPinkstack_Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUFcodellama-7bcodellama-13b-bnb-4bitopenbuddy-codellama2-34b-v11.1-bf16OpenMath-CodeLlama-13b-Python-hfQwen2.5-Coder-1.5B-Instruct-GGUF-llamafileOpenMath-CodeLlama-70b-Python-hf