Nvidia announces the Space-1 Vera Rubin space computing module, with AI computing power 25 times that of the H100.

Gate News reports that on March 17, NVIDIA announced its entry into the space computing field at GTC, unveiling the Space-1 Vera Rubin module, designed specifically for on-orbit data centers. The module integrates 2 Rubin GPUs and 1 Vera CPU, with AI inference power up to 25 times that of H100, enabling large language models and foundational models to run directly in orbit. NVIDIA founder Jensen Huang stated, “Space computing, the final frontier, has arrived. As satellite constellations are deployed and deep space exploration advances, intelligence must exist where data is generated.” He also admitted that space cooling remains an unresolved engineering challenge: “In space, there is no conduction, no convection—only radiation. We need to figure out how to cool these systems in space.” The Space-1 module is designed for environments with size, weight, and power constraints, supporting on-orbit autonomous analysis, real-time data processing, and scientific discovery. The initial partners include space solar company Aetherflux, private space station developer Axiom Space, satellite communication firm Kepler Communications, Earth observation company Planet Labs, Sophia Space, and cloud computing satellite company Starcloud. The specific launch date has not yet been announced.