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.
SmolLM-1.7B-Instruct-quantized.w4a16gemma-3-27b-it-quantized.w4a16Qwen2.5-1.5B-quantized.w8a8gemma-3-12b-it-quantized-W4A16Qwen3.5-9B-quantized.w8a8Qwen3-VL-8B-Instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w4a16glove-6B-quantizedQwen3.5-9B-quantized.w4a16Llama-3.2-1B-quantized.w8a8granite-3.1-2b-instruct-quantized.w4a16Qwen2.5-VL-3B-Instruct-quantized.w8a8DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16Llama-4-Scout-17B-16E-Instruct-quantized.w4a16Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16Qwen3-30B-A3B-Instruct-2507-quantized.w4a16Llama-3.2-3B-quantized.w8a8Qwen3-8B-quantized.w4a16Qwen2.5-VL-7B-Instruct-quantized.w8a8Meta-Llama-3.1-8B-Instruct-quantized.w8a8mlx-FLUX.1-schnell-4bit-quantizedgemma-3-27b-it-quantized-W4A16Qwen3-0.6B-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w4a16NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16Llama-3.2-1B-Instruct-quantized.w8a8MIstral-QUantized-70b_Miqu-1-70b-iMat.GGUFgemma-3-12b-it-quantized.w4a16SpeculatorLlama3-1-8B-Eagle3-converted-0717-quantizedSpeculator-Qwen3-8B-Eagle3-converted-071-quantized