• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Announcement

Nvidia Rubin is claimed to deliver 4.23x GB300 NVL72's inference performance per dollar

SemiAnalysis says the comparison uses SGLang, which it describes as a widely used production LLM engine.

NVIDIA AINA
SGLangSG
3 Sources, 2h ago, first seen 2h ago

TLDR

SemiAnalysis claims Nvidia Rubin delivers 4.23 times the inference performance per dollar of GB300 NVL72 on SGLang, an LLM engine it describes as widely used in production.

Combined views

1.9K

3 Sources, first seen 2h ago

6 likes2 comments1 saves6 reposts

Combined views

1.9K

3 Sources, first seen 2h ago

6 likes2 comments1 saves6 reposts
Image: @SemiAnalysis_ on X

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

3 Sources

SemiAnalysis@SemiAnalysis_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)🧵2h
SGLang@sgl_projectQwen3.8 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!43m
NVIDIA AI@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…42m
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    3 Sources

    SemiAnalysis@SemiAnalysis_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)🧵2h
    SGLang@sgl_projectQwen3.8 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!43m
    NVIDIA AI@NVIDIAAIRT @sgl_project: Qwen3.8 Flash Next on Vera Rubin with NVIDIA Dynamo + SGLang: Up to 6.6× throughput per chip and up to 76% lower modeled…42m
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet