Nvidia’s Vera Rubin is months away — Blackwell is getting faster right now

Source: VentureBeat

Overview

The big news this week from Nvidia, splashed in headlines across all forms of media, was the company’s announcement about its Vera Rubin GPU. This week, Nvidia CEO Jensen Huang used his CES keynote to highlight performance metrics for the new chip. According to Huang, the Rubin GPU is capable of 50 % higher performance per watt compared to the previous generation, and it introduces a new architecture that aims to accelerate AI workloads while reducing power consumption.

In addition to the performance claims, Huang noted that the Vera Rubin chip will be available in the coming months, positioning it as a bridge between the current Blackwell series and future GPU generations. The announcement also hinted at software stack improvements that will further optimize AI model training and inference on the new hardware.

Overall, Nvidia’s roadmap suggests a rapid iteration cycle, with Vera Rubin serving as a stepping stone toward more advanced, energy‑efficient GPUs that can handle increasingly complex AI tasks.