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.
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUFgpt-oss-120b-GGUFgpt-oss-20b-GGUFstories15M_MOEQwen3-0.6B-GGUFQwen3-Coder-30B-A3B-Instruct-Q8_0-GGUFQwen3-4B-Instruct-2507-Q8_0-GGUFQwen2.5-Coder-1.5B-Q8_0-GGUFDeepSeek-V4-Flash-0731-GGUFNVIDIA-Nemotron-3-Nano-30B-A3B-GGUFQwen2.5-Coder-1.5B-Instruct-Q8_0-GGUFQwen2.5-Coder-14B-Instruct-Q8_0-GGUFQwen2.5-Coder-7B-Q8_0-GGUFLaguna-XS-2.1-GGUFQwen2.5-Coder-3B-Q8_0-GGUFSmolLM2-135M-GGUFQwen3-8B-GGUFQwen2.5-Coder-7B-Instruct-Q8_0-GGUFabliterated-minicpm5-2b-ggmlfunctiongemma-270m-it-GGUFQwen2.5-Coder-3B-Instruct-Q8_0-GGUFDeepSeek-V4-Flash-GGUFMamba-gpt-3B-v4-ggml-and-ggufGLM-4.5-Air-GGUFqwen3-5-2b-q4-k-m-ggml-llama-cpp-vivo-x300Qwen2.5-Coder-0.5B-Q8_0-GGUFMeta-Llama-3.1-8B-Instruct-Q4_0-GGUFLlama-2-7B-GGUFQwen3-30B-A3B-Instruct-2507-Q8_0-GGUFQwen2.5-Coder-14B-Q8_0-GGUF