On May 18, 2026, Agentic AI inference at one-tenth the cost per token with NVIDIA Vera Rubin NVL72 . Agent sandboxes run 50% faster on NVIDIA Vera than traditional CPUs — while enterprise data queries are up to 3x faster with the Vera CPU.
What the source shows
And 5,000 enterprises like Lilly, Samsung and Honeywell are running AI workloads on Dell AI Factories with NVIDIA, turning ambition into production at scale. Dell sized the stakes: Worldwide AI infrastructure spending could reach $3-4 trillion by 2030, with token consumption projected to grow 3,400% in the same window. “There is a massive AI investment boom thats already underway, and a productivity boom is beginning, and in some companies, including ours,” Dell said. “The rate of change has gone parabolic, and it’s not slowing down.” Then, the Dell chairman and CEO welcomed NVIDIA founder and CEO Jensen Huang to the keynote stage — with a look at the NVIDIA portfolio behind him, from a deskside Dell Pro Max with GB10 workstation to a Dell PowerRack with NVIDIA Vera Rubin NVL72. “We’ve now arrived at the era of useful AI, which is the reason why demand is going parabolic, utterly parabolic,” Huang said. “What took months now takes weeks. A New AI Factory for the Agentic Era The accelerated computing news leads the refresh: The Dell PowerEdge XE9812, built on NVIDIA Vera Rubin NVL72, delivers up to 10x lower cost-per-token than NVIDIA Blackwell for massive-scale agentic AI inferencing. It’s joined by PowerEdge XE9880L, XE9885L and XE9882L servers — the first Dell systems built on NVIDIA HGX Rubin NVL8 , supporting up to 144 GPUs per rack with 100% direct liquid-cooled compute nodes and up to 5.5x the performance of HGX B200.
Why it matters
In addition, networking gets the new Dell PowerSwitch portfolio with NVIDIA Quantum-X800 InfiniBand , featuring liquid-cooled, co-packaged optics and NVIDIA Spectrum-6 Ethernet . With 1.2 TB/s memory bandwidth and predictable performance under load, Vera completes agentic workloads 50% faster than x86 processors, helping PowerEdge systems increase AI factory output with faster agent responses and shorter feedback loops. “Vera CPU has the highest single-threaded performance of any CPU in the world,” Huang said. “It has three times the memory bandwidth — as a result, Starburst, DuckDB, all these databases run incredibly fast, because the agents are pounding on the databases, so the CPU had better be super fast.” Starburst, a new data engine in the Dell AI Data Platform with NVIDIA , delivers 3x faster query throughput on NVIDIA Vera CPU for large-scale SQL analytics. He described technology as key to delivering cutting-edge science, at scale. “I think we’re on the verge of maybe being able to end disease as we know it,” Rau said. “Something like that was completely unimaginable 20 years ago, but today we can imagine it.” A video from Samsung followed — highlighting use cases for R&D chip design and manufacturing running on Dell AI Factory with NVIDIA. Agents and Models on Premises — Securely Dell’s own AI adoption survey, cited from the keynote stage, found that 67% of AI workloads now run outside the cloud — on premises, on device, at the edge or in colocation — and that 88% of respondents are running at least one AI workload on premises.
Key Questions
Q: What happened or was found?
A: On May 18, 2026, Agentic AI inference at one-tenth the cost per token with NVIDIA Vera Rubin NVL72 . Agent sandboxes run 50% faster on NVIDIA Vera than traditional CPUs — while enterprise data queries are up to 3x faster with the Vera CPU.
Q: What concrete evidence or constraint does the source provide?
A: Agent sandboxes run 50% faster on NVIDIA Vera than traditional CPUs — while enterprise data queries are up to 3x faster with the Vera CPU.
Source: NVIDIA CEO Jensen Huang at Dell Technologies World: 'Demand Is Going Parabolic, Utterly Parabolic'
Domain: blogs.nvidia.com
Comments load interactively on the live page.