Nvidia Unveils Vera Rubin AI Platform at CES 2026

At the 2026 Consumer Electronics Show in Las Vegas, Nvidia unveiled its Vera Rubin computing platform, designed to advance AI data center capabilities. The platform integrates the Rubin GPU and Vera CPU, both manufactured using TSMC's 3nm process and featuring HBM4 memory. Nvidia CEO Jensen Huang announced that Vera Rubin is scheduled for release in the third quarter of 2026.

The Rubin GPU is engineered to deliver 50 petaflops of FP4 performance, a 2.5x increase over its predecessor, Blackwell. This enhancement aims to meet the growing computational demands of AI applications.

Nvidia has also entered into a non-exclusive licensing agreement with Groq, a startup specializing in inference chips optimized for real-time chatbot performance. This partnership underscores Nvidia's commitment to advancing AI inference capabilities.

Major cloud providers, including Microsoft Azure and Google Cloud, are expected to be among the first to deploy the Vera Rubin platform. Computing companies like Dell and Cisco plan to incorporate the new chips into their data centers, while AI labs such as OpenAI and Anthropic are likely to adopt the technology for training and delivering more sophisticated AI solutions.

Nvidia's unveiling of Vera Rubin at CES 2026 highlights the company's ongoing efforts to provide advanced hardware solutions that support the evolving needs of AI development and deployment.