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.
Qwen3.8-27B-SmoothQuant-W8A8-INT8Qwen3.8-27B-heretic-SmoothQuant-W8A8-INT8LLMQ_-_LLaMA-3-8B-SmoothQuant-4bit-4bit-ggufsmoothquant-qwen25-15b-g52xlargesmoothquant-granite33-2b-g52xlargellama-3.1-8b-instruct-smoothquant-fp16-GGUFinternlm3-8b-instruct-smoothquant-fp8smoothquant-gemma2-2b-g52xlargeQwen3-VL-2B-Instruct-SmoothQuant-W8A8-FP8Swift-Qwen3.8-27b-heretic-SmoothQuant-W8A8-INT8Meta-llama3-8b-Instruct-SmoothQuant-Fp8opt-125m-smoothquantopt-1.3b-smoothquantQwen3-8B-smoothquant-w4a8Qwen3-4B-Instruct-2507-w8a8-smoothquantQwen3-1.7B-SmoothQuant_0.5_PTQ_W8A8internlm3-8b-instruct-smoothquant-int8Qwen3-VL-30B-A3B-Instruct-SmoothQuant-W8A8Qwen3.6-35B-A3B-MXFP4-MOE-SMOOTHQUANTQwen3-30B-A3B-SmoothQuant-W8A8Qwen2.5-VL-7B-Instruct-W8A8-SmoothQuantopt-6.7b-smoothquantopt-2.7b-smoothquantopt-13b-smoothquantQwen3-VL-4B-Instruct-SmoothQuant-W8A8-FP8Qwen3-1.7B-SmoothQuant_0.5_GPTQ_W4A16_GGUFLLaMA-3-8B-SmoothQuant-8bit-8bitLlama-3.1-8B-Instruct-LC-SmoothQuant-RTN-W4A16Llama-3.1-8B-Instruct-LC-SmoothQuant-GPTQ-W4A16Olmo-3-7B-Think-w8a8-smoothquant
