vLLM Day-0 Support for Qwen3.8-2.4T-A95B: Runs on Single NVIDIA/AMD Nodes

vllm_project · x · 2026-08-13

Congratulations to Alibaba Qwen on the release of Qwen3.8-2.4T-A95B, one of the largest open-weight models to date, featuring 2.4T total parameters, 95B active parameters, and 512 experts.

vLLM project has announced Day-0 support for this massive model, verified on both NVIDIA and AMD hardware. Ready-made 4-bit checkpoints are provided out of the box:

Related event: vLLM Announces Day-0 Support for Qwen3.8 2.4T Model(2 posts)→

Original post →

More from Infra

Infra channel →