Germany’s LRZ Announces Blue Lion Supercomputer Powered by NVIDIA Vera Rubin Architecture
Germany’s Leibniz Supercomputing Centre (LRZ), part of the Gauss Centre for Supercomputing, is stepping into a new era of high-performance computing with the announcement of its upcoming supercomputer — Blue Lion. This next-generation system will offer approximately 30 times more computing power than its predecessor, SuperMUC-NG.
What makes Blue Lion especially notable is its architecture. It will be based on NVIDIA’s new Vera Rubin platform, marking a major leap forward for scientific computing and AI in Europe. Until now, LRZ had only mentioned plans to use “next-generation” NVIDIA technologies — now it’s confirmed that Vera Rubin is the foundation.
What Is NVIDIA Vera Rubin?
Vera Rubin is NVIDIA’s cutting-edge supercomputing platform designed to unify AI, data analytics, and simulation workloads. At its core, the platform features:
- Rubin GPU – the successor to NVIDIA’s Blackwell GPUs
- Vera CPU – NVIDIA’s first custom-designed CPU, optimized to work in tandem with the Rubin GPU
Together, they form a highly integrated, high-bandwidth, low-latency platform. The architecture supports shared memory, coherent compute operations, and in-network acceleration, allowing science applications to run faster and more efficiently than ever before.
The Vera Rubin platform is scheduled to launch in the second half of 2026.
A Global Push for Scientific Computing
LRZ’s Blue Lion is not alone. Just weeks ago, the Lawrence Berkeley National Laboratory in the United States unveiled its own Vera Rubin-powered system, Doudna. Two major institutions — on two continents — are now preparing to adopt the same architecture, signaling global confidence in NVIDIA’s new direction for supercomputing.
With Blue Lion, Germany reinforces its position at the forefront of scientific innovation, preparing researchers for the next wave of breakthroughs in climate modeling, physics, AI, and beyond.
About the System
HPE is building Blue Lion. It will use next-generation HPE Cray technology and feature NVIDIA GPUs in a system equipped with powerful storage and interconnect that harnesses HPE’s 100% fanless direct liquid-cooling systems architecture, which uses warm water delivered through pipes to efficiently cool the supercomputer.