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.
Qwen_Qwen3-Coder-30B-A3B-Instruct-GGUFQwen2.5-0.5B-Instruct-GGUFllama3.2-1b-Uncensored-GGUFQwen_Qwen3-30B-A3B-GGUFLlama3-1B-Base-GGUFQwen_Qwen3-1.7B-GGUFQwen2.5-7B-Instruct-Uncensored-GGUFQwen_Qwen3-8B-GGUFQwen2.5-1.5B-Instruct-GGUFQwen2.5-32B-Instruct-abliterated-GGUFQwen2.5-3B-Instruct-abliterated-GGUFPhi-4-mini-instruct-abliterated-GGUFDarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUFLlama-3.2-1B-Instruct-GGUFDeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUFhuihui-ai_Huihui-Qwen3-4B-abliterated-v2-GGUFQwen_Qwen3-14B-GGUFQwen2.5-Coder-14B-Instruct-abliterated-GGUFQwen_Qwen3-0.6B-GGUFQwen1.5-MoE-A2.7B-Chat-GGUFLlama-3-Groq-8B-Tool-Use-GGUFLlama-3.2-3B-Instruct-GGUFcyber-risk-llama-3-8b-instruct-sft-GGUFPhi-4-mini-instruct-GGUFgemma-2-2b-it-GGUFDeepSeek-V3-1B-Test-GGUFQwen2.5-3B-Instruct-GGUFbloomz-3b-sft-chat-GGUFArabic-llama3.1-16bit-FT-GGUFgranite-20b-code-base-8k-GGUF