On Sunday, Nvidia Chief Executive Jensen Huang announced that the company’s next-generation artificial intelligence (AI) chip platform, Rubin, will be introduced in 2026.
The announcement was made during a presentation at National Taiwan University as part of the Computex trade show.
The Rubin platform will encompass new graphics processing units (GPUs), central processing units (CPUs), and networking chips. Huang, however, provided limited specifics about the new products.
The forthcoming CPU in the Rubin family will be called Versa. The new GPUs, designed to enhance AI applications, will incorporate next-generation high-bandwidth memory produced by companies such as SK Hynix, Micron, and Samsung.
Huang indicated that Nvidia will now release a new family of AI chips annually, accelerating its previous cycle of releasing new products approximately every two years.
With approximately 80% market share in AI chips, Nvidia is both a major enabler and a key beneficiary of the rapid growth in AI development. The company’s dominant position in the market places it at the forefront of technological advancements in AI hardware.
