Nvidia Chief Executive Jensen Huang has delivered the company’s latest artificial intelligence device, the DGX Spark, to Elon Musk at SpaceX’s Starbase site in Texas. The compact system, weighing about 1.2 kilograms, is described by Nvidia as the smallest AI supercomputer built to date, capable of running models with up to 200 billion parameters locally.

Huang’s visit coincided with preparations for the 11th test flight of SpaceX’s Starship rocket, currently the most powerful launch vehicle in the world. The Nvidia chief called the handoff a “full-circle moment,” referencing his earlier delivery of the first DGX system to OpenAI several years ago.

“Imagine delivering the smallest supercomputer next to the biggest rocket,” Huang said during the visit, where he met with Musk and SpaceX engineers.

The DGX Spark delivers up to one petaflop of AI performance and is powered by Nvidia’s new GB10 Grace Blackwell Superchip. It includes 128GB of unified memory, NVLink-C2C connectivity, and NVMe storage, offering data center–grade performance in a compact form factor aimed at developers, researchers, and creators.

The launch of DGX Spark underscores Nvidia’s strategy to expand its AI ecosystem beyond large data centers, targeting edge computing and on-device model development. Analysts say the move could strengthen Nvidia’s dominance in the AI hardware market by making high-performance computing more accessible to smaller labs, start-ups, and individual developers.

Disclaimer: The news articles published on Fluxx News are based on reports from reputable third-party sources and are not original reporting by Fluxx News. While we strive to ensure accuracy and integrity, we cannot guarantee the completeness or timeliness of the information provided.