VOOZH about

URL: https://www.phoronix.com/review/google-cloud-n4a-axion/5

⇱ Google Axion CPU Performance With The New Google Cloud N4A Instances Review - Phoronix


👁 Phoronix

Google Axion CPU Performance With The New Google Cloud N4A Instances

Written by Michael Larabel in Cloud on 27 January 2026 at 12:00 PM EST. Page 5 of 5. 12 Comments.

From heavy computational workloads to code compilation to databases and scripting language performance, the Google Cloud N4A instances were an all-around winner in performance and value compared to the prior-generation Tau T2A instances. Very solid generational gains and impressive in quantifying the performance uplift from Arm Neoverse N1 to now N3 based cores.

Across the span of around 75 benchmarks carried out, on a geo mean basis when running at the same standard 16 vCPU instance size, the N4A instance delivered 1.77x the performance of the T2A based instance. While the cost of the N4A standard 16 vCPU instance was about 11% higher than T2A, it's easily justified with the much stronger performance to make it the more cost effective option. The Google Cloud N4A instances should also be more energy efficient too but no power sensors/metrics are exposed to the Google Cloud VM to independently quantify that difference.

Thanks to Google for providing the gratis access to the N4A instance family while in preview to be able to run these benchmarks for today's GA debut.

If you enjoyed this article consider joining Phoronix Premium to view this site ad-free, multi-page articles on a single page, and other benefits. PayPal or Stripe tips are also graciously accepted. Thanks for your support.

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.