Qwen3.8-Flash-Next hits 685 output tokens/s per user with TokenSpeed on GB300
AI summary
The LightSeek Foundation reports that Alibaba's Qwen3.8-Flash-Next reached 685 output tokens per second per user, running its TokenSpeed serving stack on 4× NVIDIA GB300 GPUs with NVFP4 precision. Alibaba's Qwen account amplified the result on X, thanking LightSeek and saying it is excited to see the community unlock more of Qwen's inference potential. LightSeek said a blog post details the kernel and serving optimizations behind the numbers, with the code available on GitHub.
In-depth insight
Serving optimizations like these matter for high-concurrency deployment of open-weight models, though the figure is a partner-reported benchmark shared to showcase Qwen's inference potential.