vLLM-Kunlun

community

AI & ML interests

vLLM-Kunlun can deploy models with various torch dtype weights, which can be downloaded here.

vLLM-Kunlun 's models 4

vLLM-Kunlun/GLM-5-W8A8-INT8-Dynamic

vLLM-Kunlun/Qwen3-4B-Int8-Dynamic

4B • Updated Feb 3

vLLM-Kunlun/Qwen3-235B-A22B-Instruct-2507-Int8-Dynamic

vLLM-Kunlun/MiMo-V2-Flash-BF16

Updated Dec 31, 2025