Rubin will reduce the cost of running AI models to about one-tenth that of Nvidia’s current leading chip system, Blackwell, the company told analysts and reporters during a call Sunday. Nvidia also said that Rubin could train somewhat larger models using about one-quarter the number of chips that Blackwell required. Overall, those benefits could make advanced AI systems significantly cheaper to operate and make it harder for Nvidia customers to justify moving away from its hardware.
Nvidia said on the call that two of its existing partners, Microsoft and CoreWave, will be among the first companies to start offering services powered by Rubin chips later this year. Nvidia said that two major AI data centers that Microsoft is currently building in Georgia and Wisconsin will eventually contain thousands of Rubin chips. Some of Nvidia’s partners have begun running their next-generation AI models on early Rubin systems, the company said.
The semiconductor giant also said it is working with Red Hat, which makes open source enterprise software for banks, automakers, airlines and government agencies, to offer more products running on the new Rubin chip system.
Nvidia’s latest chip platform is named after Vera Rubin, the American astronomer who reshaped the way scientists understand the properties of galaxies. The system consists of six different chips, including the Rubin GPU and Vera CPU, both of which are fabricated using Taiwan Semiconductor Manufacturing Company’s 3-nanometer fabrication process and the most advanced high-bandwidth memory technology available. Nvidia’s sixth-generation interconnect and switching technologies connect different chips together.
Every part of this chip system is “completely revolutionary and the best of its kind,” Huang announced during the company’s CES press conference.
Nvidia has been developing Rubin systems for years, and Huang first announced that the chips are coming in 2024 during a keynote speech. Last year, the company said systems built on Rubin would begin arriving in the second half of 2026.
It’s not clear exactly what Nvidia means by saying that Vera Rubin is in “full production.” Typically, production of these advanced chips – which Nvidia is making with its longtime partner TSMC – starts in small quantities while the chips undergo testing and validation and are scaled up at a later stage.
<a href