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 Energy Efficiency(6 posts)→
More from Infra
- The shadow GPU capacity market is formalizing, with Meta selling excess compute to outside buyers — DavidLinthicum · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- LLM Serving Metrics Thread: Why TPOT and Uptime Make or Break User Experience — abhijithneil · 2026-09-11