GoKawiilOracle Cloud adds standalone Nvidia Vera CPU instances alongside Vera Rubin NVL72 rollout
Nvidia and Oracle announced general availability of Nvidia's Vera Rubin NVL72 racks and standalone Vera CPU instances on Oracle Cloud Infrastructure Superclusters at Oracle AI World. The move follows Google Cloud's similar Vera Rubin availability announcement last week. Separately, independent benchmarks on a Vera server (not run on OCI hardware) showed significantly higher memory bandwidth than a dual Xeon 6 system.
GoKawiil's interpretation of the reporting above, not reported fact.
Offering Vera as a standalone CPU, rather than only paired with GPUs, marks Nvidia's first push into hyperscaler data centers as a general-purpose CPU option alongside entrenched x86 and Arm choices like Ampere Altra. Nvidia's Ian Buck has said a single 88-core chip can't serve the whole market, suggesting this is an opening move that could expand in future CPU generations rather than an immediate challenge to AMD and Intel, who still lead in core density and are set to extend that lead with AMD's upcoming EPYC Venice chips.
- Nvidia Vera Rubin NVL72 racks and standalone Vera CPUs are now generally available on Oracle Cloud Infrastructure Superclusters.
- Independent benchmarks show Vera's memory bandwidth far exceeds a dual Xeon 6 server, though tests weren't run on OCI hardware.
- This marks Nvidia's first standalone CPU offering at a major hyperscaler, positioned alongside x86 and Ampere Altra instances.
Source: tomshardware.com — Jake Roach, 2026-10-28
Published there as: “Standalone Nvidia Vera CPUs land in Oracle Cloud's multi-gigawatt deployment — our independent benchmarking of a local server reveals Vera's massive memory bandwidth lead over dual Xeon 6 server”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.