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.w4a16Qwen2.5-1.5B-quantized.w8a8granite-3.1-2b-instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w4a16Meta-Llama-3.1-8B-Instruct-quantized.w8a8Qwen3-8B-quantized.w4a16Qwen3-0.6B-quantized.w4a16DeepSeek-R1-Distill-Qwen-32B-quantized.w4a16Qwen3-32B-quantized.w4a16Meta-Llama-3.1-70B-Instruct-quantized.w4a16NVIDIA-Nemotron-3-Ultra-550B-A55B-quantized.w4a16Qwen3-4B-quantized.w4a16Llama-3.2-1B-Instruct-quantized.w8a8Qwen3-30B-A3B-Instruct-2507-quantized.w4a16Qwen3-30B-A3B-Instruct-2507-quantized.w8a8Llama-3.3-70B-Instruct-quantized.w4a16Mistral-Small-24B-Instruct-2501-quantized.w4a16Mistral-Nemo-Instruct-2407-quantized.w4a16Mistral-Small-24B-Instruct-2501-quantized.w8a8phi-4-quantized.w8a8Qwen3-30B-A3B-quantized.w4a16MiniCPM5-2B-RotSVDMix-Quantizedgranite-3.1-8b-instruct-quantized.w4a16phi-4-quantized.w4a16granite-4.1-3b-quantized.w8a8Phi-3-medium-128k-instruct-quantized.w4a16Qwen3-4B-Instruct-2507-quantized.w8a8Llama-3.3-70B-Instruct-quantized.w8a8Qwen2.5-7B-Instruct-quantized.w8a8Meta-Llama-3.1-70B-Instruct-quantized.w8a8