NVIDIA launches Vera Rubin with 10x better performance per watt
nvidia · x · 2026-07-22
NVIDIA says the Vera Rubin platform is here, claiming 10x better performance per watt.
- The company says the Vera Rubin NVL72 is being deployed across its ecosystem, including CoreWeave, Google Cloud, Microsoft, and Oracle Cloud, to target the “agentic era” with lower token cost.
- NVIDIA says CoreWeave measured 10x more tokens per megawatt on Vera Rubin NVL72 than Blackwell in its first benchmark.
- It also says Vera CPU is more than 2x faster in results from DeepInfra, with support for more concurrent AI agents than other CPUs.
Related event: NVIDIA Launches Vera Rubin with 10x Performance Per Watt(4 posts)→
More from Infra
- PoLar: Dynamically Skipping or Looping LLM Layers for Efficient Inference — ttkciar · 2026-07-22
- SK Hynix CEO: Next Year Will Be the Worst Year in Industry's History from Supply Perspective — Beth_Kindig · 2026-07-22
- Tabul AI launches Metal TreeSHAP to speed up Shapley values on Apple silicon — Scobleizer · 2026-07-22
- Tech Giants Are Hiding $1.6T in AI Debt Using Enron's Trick — arto · 2026-07-22
- DeepSeek-V4-Flash tops out at 770 tok/s on one B300 in a vLLM batch test — Moreh · 2026-07-22
- NVIDIA starts shipping 102.4 Tbps Spectrum-6 switches for Vera Rubin AI factories — nvidia · 2026-07-22