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.
Qwen3-VL-30B-A3B-Instruct-AWQSmolLM-1.7B-Instruct-quantized.w4a16GLM-4.7-Flash-AWQQwen3-Coder-30B-A3B-Instruct-AWQMeta-Llama-3.1-8B-Instruct-AWQ-INT4Meta-Llama-3.1-70B-Instruct-AWQ-INT4Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8Qwen2.5-1.5B-quantized.w8a8Llama-3.2-1B-Instruct-Q4_K_M-GGUFQwen2.5-Coder-7B-GGUFMeta-Llama-3.1-8B-Instruct-quantized.w4a16Meta-Llama-3-8B-Instruct-GGUFNVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16Llama-3.2-3B-Instruct-Q4_K_M-GGUFgranite-3.1-2b-instruct-quantized.w4a16gemma-2-9b-it-AWQ-INT4Nanbeige4.1-3B-Q8_0-GGUFDeepSeek-R1-Distill-Qwen-32B-quantized.w4a16Qwen3-30B-A3B-Instruct-2507-quantized.w4a16Solar-Open2-250B-Mixed-Quant-GGUFQwen3-VL-30B-A3B-Thinking-AWQQwen3-8B-quantized.w4a16Qwen2.5-7B-Instruct-Uncensored-GGUFNanbeige4.1-3B-Q4_K_M-GGUFMeta-Llama-3.1-8B-Instruct-quantized.w8a8Qwen2.5-7B-Instruct-abliterated-v2-GGUFCotype-Nano-GGUFQwen3-0.6B-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w4a16DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF