aiqbench analysis
Nvidia's upcoming Rubin HPC architecture introduces a specialized cluster of 898 Tensor cores optimized for large language models alongside over 28,000 CUDA cores for general scientific simulations. The chip will also feature sparse data acceleration to handle zero-heavy datasets common in astrophysics and biology, with shipping targeted for 2028.
At SC26, Nvidia debuts new Rubin HPC chip, scientific research libraries
From SiliconANGLE
ExcerptNvidia Corp. today introduced a set of offerings designed to speed up scientific research across a range of fields.
The lineup is headlined by Rubin HPC, an upcoming graphics card with significantly more cores than the company’s current flagship chip. It’s joined by more than a half-dozen software tools geared toward scientists and engineers. The technologies made their debut at the SC26 high-performance and supercomputing conference in Chicago.
Nvidia’s flagship Rubin graphics processing unit features 898 Tensor cores, transistor clusters specifically optimized for large language models.
Excerpt shown under the publisher's RSS terms · 86 words · full text and figures are on the publisher's site
Other coverage of this story
Related coverage

IEEE Xplore Digital Library Adds AI Assistant
IEEE Spectrum · Oct 26, 2026

Run High-Performance Core Math at Scale with NVIDIA nvmath-python
NVIDIA · Jul 30, 2026
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
arXiv · Sep 2, 2026
SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution Feedback
arXiv · Sep 25, 2026