SGLang says Qwen3.8 Flash Next on NVIDIA Vera Rubin, running with NVIDIA Dynamo and SGLang, delivers up to 6.6× throughput per chip versus GB300. It also reports up to 76% lower modeled cost per total token at matched per-user speed. SemiAnalysis's separate analysis puts Rubin at 4.23× performance per dollar over GB300 NVL72 on SGLang.
Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang:
Up to 6.6× throughput per chip and up to 76% lower modeled cost per total token vs. GB300, at matched per-user speed.
Thanks @NVIDIAAI for the partnership and early access, and @SemiAnalysis_ for the results!
ALERT🚨: NVIDIA SGLANG INFERENCE RUBIN IS 4.23x BETTER 🚀 PERF PER DOLLAR THAN EVEN GB300 NVL72. This is on the widely used production LLM engine called @sgl_project. (1/2)🧵
Source: SGLang · x.comPublished · added here
