MENU

NVIDIA Vera CPU: Agent Performance and Throughput vs x86

NVIDIA Blog USA
Overview
NVIDIA Vera delivers industry-leading agent speed and 1.6x more agents per watt compared to the fastest x86 CPUs. By combining high throughput with energy efficiency, it eliminates the need for providers to mix different x86 parts to balance speed and capacity.
In Depth

Key Findings

NVIDIA Vera outperforms both the fastest and most energy-efficient x86 CPUs in a 100-megawatt data center comparison. Specifically, Vera provides 1.6x more agents per watt than the fastest x86 CPU and delivers 2x faster agent speed than the most energy-efficient x86 CPU.

Technical Details and Partner Benchmarks

Early production-style tests from various partners demonstrate the CPU’s performance across different agentic workloads:

  • Perplexity: Executed agentic coding tasks 1.5x faster than traditional CPUs.
  • DeepInfra: Achieved up to 2.2x the speed of the best x86 processor for agentic orchestration.
  • Daytona: Brought 1,000 agent sandboxes online in 10.8 seconds, compared to 88.4 seconds with x86, and reached 12.7 completed jobs per second with 2,000 concurrent sandboxes.
  • Modal: Realized up to 2x sandbox throughput per core versus comparable x86 hardware, with gains increasing under heavy load.
  • ClickHouse: Scaled near-linearly across 176 cores using a standard binary, topping the ClickBench hardware leaderboard.
  • DuckLabs: Reached approximately 1.5x the median TPC-H SF1000 performance of an Intel Xeon 6 baseline.

Background and Context

AI agents require a constant cycle between GPU reasoning and CPU execution to perform tasks such as searching for information, querying databases, and writing or testing code. As AI factories deploy more agents, they face strict power limits. This necessitates infrastructure that maximizes work per watt to prevent agents from waiting longer to complete tasks.

Significance and Outlook

The integration of fast performance and high capacity per watt into a single CPU allows infrastructure providers to support a wide range of agent workloads without mixing and matching different x86 components. This efficiency is critical for AI factories operating under power constraints, ensuring higher agent density and faster execution speeds within the same energy envelope.

Source: https://blogs.nvidia.com/blog/vera-cpu-highest-throughput-fastest-agents/

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

  • Your email and selected fields are used only to deliver the newsletter.
  • We never share your information with third parties.
  • You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Takes about a minute · Unsubscribe anytime

Published by Troy-Technical, an independent site run by one engineer with a career in materials development.
About the author / Contact info@troy-technical.jp
Let's share this post !

Author of this article

TOC