Nvidia finally reveals new Rubin GPU with almost 3X more CUDA cores than the Nvidia RTX 5090 — but you will have to wait till 2028 to grab it
Reported by TechRadar1 source ↓
Nvidia's Rubin HPC GPU packs over 50,000 CUDA cores, targets scientific simulations, and is expected to reach systems in 2028.
Key points
- Rubin HPC is designed for scientific simulations and data analysis, not consumer gaming
- Nvidia says it includes sparse data acceleration and seventh-generation NVLink
- Nvidia has not published throughput figures, and independent testing has not established workload performance
Details
Announced at the SC26 supercomputing conference, Rubin HPC is planned as an accelerator in Nvidia’s Vera Rubin platform. Nvidia says it is intended for work such as simulations of materials, molecules, industrial designs and climate systems.
The company says the chip combines processing cores with faster data movement and includes sparse data acceleration for calculations involving large datasets. Nvidia also says its seventh-generation NVLink is designed to improve communication among GPUs in larger systems. It has not published throughput figures for this implementation, and independent testing has not established how much faster specific workloads will run.
Written from coverage as of
Images
- TechRadar
Stocks in this story
Change since open: 20 Nov to 21 Nov 2026
Last refresh