Nvidia previews Vera Rubin Space-1 Module for orbital data centers

The new computing device is designed to power satellites and orbital data centers.

Mar. 16, 2026 at 11:37pm

Got story updates? Submit your updates here. ›

Nvidia has announced the Vera Rubin Space-1 Module, a computing device designed to power satellites and orbital data centers. The module is based on Nvidia's Vera chip, which combines two Rubin graphics processing units with a single Vera central processing unit. The Vera Rubin chip features 88 cores with a neural branch predictor and a memory subsystem based on LPDDR5X RAM. The Rubin graphics card can provide 50 petaflops of performance when processing NVFP4 data. Nvidia envisions customers using the Vera Rubin Space-1 Module to power not only satellites but also orbital data centers.

Why it matters

The Vera Rubin Space-1 Module represents Nvidia's latest effort to expand its presence in the space technology market. By developing specialized hardware for satellites and orbital data centers, Nvidia is positioning itself as a key player in the growing field of space-based computing and data infrastructure. This could have significant implications for the future of space exploration, satellite communications, and the development of orbital AI capabilities.

The details

The Vera Rubin Space-1 Module is based on Nvidia's Vera chip, which combines two Rubin graphics processing units with a single Vera central processing unit. The Vera chip features 88 cores with a neural branch predictor, a module that can complete some calculations before their results are needed, which helps to speed up processing. The chip's memory subsystem is based on LPDDR5X RAM, a type of RAM commonly found in consumer devices. The Rubin graphics card, the other component of the Vera Rubin, features 336 billion transistors made using a 3-nanometer node and can provide 50 petaflops of performance when processing NVFP4 data.

  • Nvidia first announced the Vera chip last year.
  • Nvidia previewed the Vera Rubin Space-1 Module during CEO Jensen Huang's GTC keynote on March 16, 2026.

The players

Nvidia

An American multinational technology company that designs graphics processing units (GPUs), application programming interfaces (APIs) for game development, and systems on a chip units (SoCs) for the mobile computing and automotive market.

Jensen Huang

The co-founder and CEO of Nvidia, who announced the Vera Rubin Space-1 Module during his GTC keynote.

Sophia Space Inc.

A company that is already using Nvidia's silicon for its space-based projects.

Aetherflux Inc.

A space-based solar farm startup that is part of Nvidia's customer base.

Planet Labs PBC

A satellite imaging and data analysis company that is also a customer of Nvidia.

Got photos? Submit your photos here. ›

What they’re saying

“In space there's no conduction, there's no convection. There's just radiation. And so we have to figure out how to cool these systems out in space. We've got lots of great engineers working on it.”

— Jensen Huang, CEO

What’s next

Nvidia has stated that it is still working on the cooling mechanism for the Vera Rubin Space-1 Module, as the lack of conduction and convection in space presents unique challenges. The company will likely continue to refine the design and seek partnerships with space technology companies to further develop and deploy the module.

The takeaway

Nvidia's Vera Rubin Space-1 Module represents a significant step forward in the company's efforts to expand its presence in the space technology market. By developing specialized hardware for satellites and orbital data centers, Nvidia is positioning itself as a key player in the growing field of space-based computing and data infrastructure, which could have far-reaching implications for the future of space exploration and satellite communications.