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.
smoothquant-qwen25-15b-g52xlargesmoothquant-granite33-2b-g52xlargellama-3.1-8b-instruct-smoothquant-fp16-GGUFsmoothquant-gemma2-2b-g52xlargeQwen3-VL-2B-Instruct-SmoothQuant-W8A8-FP8Meta-llama3-8b-Instruct-SmoothQuant-Fp8opt-1.3b-smoothquantopt-125m-smoothquantopt-2.7b-smoothquantQwen3-VL-30B-A3B-Instruct-SmoothQuant-W8A8Qwen3.6-35B-A3B-MXFP4-MOE-SMOOTHQUANTopt-6.7b-smoothquantopt-13b-smoothquantLLaMA-3-8B-SmoothQuant-8bit-8bitLlama-3.1-8B-Instruct-LC-SmoothQuant-RTN-W4A16Llama-3.1-8B-Instruct-LC-SmoothQuant-GPTQ-W4A16Qwen3-VL-4B-Instruct-SmoothQuant-W8A8-FP8LLaMA-3-8B-SmoothQuant-4bit-4bitLlama-3.1-8B-Instruct-LC-SmoothQuant-GPTQ-W8A16tinyllama-1.1b-chat-smoothquantQwen3-VL-8B-Instruct-SmoothQuant-W8A8-FP8opt-66b-smoothquantLlama-3.1-8B-Instruct-LC-SmoothQuant-GPTQ-W8A8opt-30b-smoothquantopt-125m-smoothquant-onnxLlama-2-7b-hf-smoothquant-w8a8opt-125m-smooth-quantMeta-Llama-3.1-70B-Instruct-LC-SmoothQuant-RTN-W4A16Qwen3-8B-SMOOTHQUANT-W8A8Meta-Llama-3-8B-smoothquant-w8a8