Nvidia Tests Lower-Memory Rubin Ultra Variants Amid HBM Shortages

Nvidia is reportedly testing various versions of its next-generation Rubin Ultra GPU, including designs with reduced high-bandwidth memory (HBM) capacity. The move reflects broader pressure on the semiconductor industry as soaring AI demand has strained the availability of advanced memory chips.

The company is considering lower-memory designs in part because it may not be able to secure enough HBM chips to support its original configuration. While lower memory could affect performance, AI companies running large models on reduced-memory versions may need to deploy more GPUs than they otherwise would.

The high-bandwidth memory shortage is driven by surging demand for Nvidia's AI GPUs and rising data center spending. This situation has pushed up prices and increased costs across the technology industry, forcing companies to spend more on hardware.