Today at the Consumer Electronics Show, Nvidia CEO Jensen Huang officially unveiled the company’s new Rubin computing architecture, which he described as the latest in hardware AI. The new architecture is currently in production and is expected to be further enhanced in the second half of the year.
“Vera Rubin is designed to address this fundamental challenge we have: The amount of computation required for artificial intelligence is skyrocketing.” Huang told the audience. “Today, I can tell you that Vera Rubin is in full production.”
Rubin architecture, which was announced for the first time in 2024is the latest result of Nvidia’s relentless cycle of hardware development, which has made Nvidia the most valuable company in the world. The Rubin architecture will replace the Blackwell architecture, which in turn replaced the Hopper and Lovelace architectures.
Rubin chips are already slated for use by nearly every major cloud provider, including Nvidia’s high-profile partnerships with Humane, OpenAIand Amazon Web Services. Rubin systems will also be used HPE’s Blue Lion supercomputer and the upcoming Doudna supercomputer; at Lawrence Berkeley National Lab.
Named for astronomer Vera Florence Cooper Rubin;the Rubin architecture consists of six separate chips designed to be used in concert. The Rubin GPU is at the center, but the architecture also addresses growing storage and interconnect bottlenecks with new improvements to the Bluefield and NVLink systems respectively. The architecture also includes a new Vera CPU designed for representational logic.
Explaining the benefits of the new storage, Nvidia’s senior director of AI infrastructure solutions, Dion Harris, pointed to the increasing cache-related memory requirements of modern AI systems.
“As you start to enable new types of workflows, like agent AI or long-running tasks, that puts a lot of pressure and demands on your KV cache,” Harris told reporters on a call, referring to a memory system used by AI models to condense inputs. “So we’ve introduced a new storage tier that connects externally to the computing device, which allows you to scale storage much more efficiently.”
Techcrunch event
San Francisco
|
13-15 October 2026
As expected, the new architecture also represents a significant advance in speed and power efficiency. According to Nvidia’s tests, the Rubin architecture will run three and a half times faster than the previous Blackwell architecture in model training tasks and five times faster in inference tasks, reaching 50 petaflops. The new platform will also support eight times more inference calculations per watt.
Rubin’s new capabilities come amid intense competition to build AI infrastructure, which has seen both AI labs and cloud providers vying for Nvidia chips as well as the facilities necessary to power them. In an October 2025 earnings call, Huang estimated that between $3 trillion and $4 trillion will be spent on AI infrastructure over the next five years.
