Nvidia Announces New AI-Accelerating GPUs at GTC 2025 Conference
New GPU Announcements
At Nvidia’s GTC 2025 conference in San Jose, California, CEO Jensen Huang revealed several new AI-accelerating GPUs that the company plans to release over the coming months and years. He also provided more details about previously announced chips.
Vera Rubin: The Centerpiece Announcement
The centerpiece of the announcements was Vera Rubin, first teased at Computex 2024 and now scheduled for release in the second half of 2026. This GPU, named after a famous astronomer, will feature tens of terabytes of memory and comes with a custom Nvidia-designed CPU called Vera.
Performance Improvements
According to Nvidia, Vera Rubin will deliver significant performance improvements over its predecessor, Grace Blackwell, particularly for AI training and inference.
Specifications for Vera Rubin
Specifications for Vera Rubin, presented by Jensen Huang during his GTC 2025 keynote.
[Image: Specifications for Vera Rubin, presented by Jensen Huang during his GTC 2025 keynote.]
Vera Rubin Features
- Two GPUs on one die, delivering 50 petaflops of FP4 inference performance per chip
- Configured in a full NVL144 rack, the system delivers 3.6 exaflops of FP4 inference compute
- The Vera CPU features 88 custom ARM cores with 176 threads connected to Rubin GPUs via a high-speed 1.8 TB/s NVLink interface
Rubin Ultra: The Future of AI-Acceleration
Huang also announced Rubin Ultra, which will follow in the second half of 2027. Rubin Ultra will use the NVL576 rack configuration and feature individual GPUs with four reticle-sized dies, delivering 100 petaflops of FP4 precision (a 4-bit floating-point format used for representing and processing numbers within AI models) per chip.
Rubin Ultra Specifications
- At the rack level, Rubin Ultra will provide 15 exaflops of FP4 inference compute and 5 exaflops of FP8 training performance
- Each Rubin Ultra GPU will include 1TB of HBM4e memory, with the complete rack containing 365TB of fast memory
Conclusion
Nvidia’s new GPU announcements mark a significant milestone in the company’s efforts to accelerate the development of AI and high-performance computing. With the release of Vera Rubin and Rubin Ultra, Nvidia is poised to further cement its position as a leader in the field of AI-acceleration.
FAQs
Q: When will Vera Rubin be released?
A: Vera Rubin is scheduled for release in the second half of 2026.
Q: What are the key features of Vera Rubin?
A: Vera Rubin features two GPUs on one die, delivering 50 petaflops of FP4 inference performance per chip, and a custom Nvidia-designed CPU called Vera.
Q: What is the difference between Vera Rubin and Rubin Ultra?
A: Rubin Ultra is a more powerful version of Vera Rubin, with individual GPUs featuring four reticle-sized dies and delivering 100 petaflops of FP4 precision per chip.
