Nvidia CEO Jensen Huang says that the corporate’s next-generation AI superchip platform, Vera Rubin, is on schedule to start arriving to clients later this yr. “As we speak, I can let you know that Vera Rubin is in full manufacturing,” Huang mentioned throughout a press occasion on Monday on the annual CES know-how commerce present in Las Vegas.
Rubin will lower the price of operating AI fashions to about one-tenth of Nvidia’s present main chip system, Blackwell, the corporate advised analysts and journalists throughout a name on Sunday. Nvidia additionally mentioned Rubin can practice sure giant fashions utilizing roughly one-fourth as many chips as Blackwell requires. Taken collectively, these beneficial properties might make superior AI methods considerably cheaper to function and make it more durable for Nvidia’s clients to justify shifting away from its {hardware}.
Nvidia mentioned on the decision that two of its present companions, Microsoft and CoreWeave, shall be among the many first firms to start providing providers powered by Rubin chips later this yr. Two main AI information facilities that Microsoft is presently constructing in Georgia and Wisconsin will ultimately embody hundreds of Rubin chips, Nvidia added. A few of Nvidia’s companions have began operating their next-generation AI fashions on early Rubin methods, the corporate mentioned.
The semiconductor large additionally mentioned it’s working with Pink Hat, which makes open supply enterprise software program for banks, automakers, airways, and authorities businesses, to supply extra merchandise that may run on the brand new Rubin chip system.
Nvidia’s newest chip platform is called after Vera Rubin, an American astronomer who reshaped how scientists perceive the properties of galaxies. The system contains six totally different chips, together with the Rubin GPU and a Vera CPU, each of that are constructed utilizing Taiwan Semiconductor Manufacturing Firm’s 3-nanometer fabrication course of and probably the most superior bandwidth reminiscence know-how accessible. Nvidia’s sixth-generation interconnect and switching applied sciences hyperlink the varied chips collectively.
Every a part of this chip system is “utterly revolutionary and the perfect of its sort,” Huang proclaimed throughout the firm’s CES press convention.
Nvidia has been creating the Rubin system for years, and Huang first introduced the chips have been coming throughout a keynote speech in 2024. Final yr, the corporate mentioned that methods constructed on Rubin would start arriving within the second half of 2026.
It’s unclear precisely what Nvidia means by saying that Vera Rubin is in “full manufacturing.” Sometimes, manufacturing for chips this superior—which Nvidia is constructing with its longtime companion TSMC—begins at low quantity whereas the chips undergo testing and validation and ramps up at a later stage.
“This CES announcement round Rubin is to inform buyers, ‘We’re on monitor,’” says Austin Lyons, an analyst at Artistic Strategists and creator of the semiconductor trade e-newsletter Chipstrat. There have been rumors on Wall Road that the Rubin GPU was operating delayed, Lyons says, so Nvidia is now pushing again by saying it has cleared key improvement and testing steps, and it’s assured Rubin continues to be on track to start scaling up manufacturing within the second half of 2026.
In 2024, Nvidia needed to delay supply of its then-new Blackwell chips attributable to a design flaw that prompted them to overheat once they have been linked collectively in server racks. Shipments for Blackwell have been again on schedule by the center of 2025.
Because the AI trade quickly expands, software program firms and cloud service suppliers have needed to fiercely compete for entry to Nvidia’s latest GPUs. Demand will possible be simply as excessive for Rubin. However some companies are additionally hedging their bets by investing in their very own customized chip designs. OpenAI, for instance, has mentioned it’s working with Broadcom to construct bespoke silicon for its subsequent era of AI fashions. These partnerships spotlight a longer-term threat for Nvidia: Prospects that design their very own chips can achieve a degree of management over their {hardware} that the corporate doesn’t provide.
However Lyons says immediately’s bulletins reveal how Nvidia is evolving past merely providing GPUs to changing into a “full AI system architect, spanning compute, networking, reminiscence hierarchy, storage, and software program orchestration.” Whilst hyperscalers pour cash into customized silicon, he provides, Nvidia’s tightly built-in platform “is getting more durable to displace.”
