- JUPITER is the first exascale spacecraft in Europe and the fourth in the world, operating in Jülich.
- Architecture with 24.000 GH200, InfiniBand Quantum-2 and Green500-leading JEDI module.
- Applications in climate, AI, biomedicine, quantum mechanics, and open access via EuroHPC.
In the midst of the digital frenzy and with artificial intelligence advancing by leaps and bounds, supercomputing has become the yardstick by which the technological capacity of a country or continent is measured. On that chessboard, Europe has just made a move with an epoch-making move: JUPITER, his first fully operational exascale system, is already underway in Germany.
We're not talking about just another machine. We're talking about a league leap. While the United States has led the way in recent years with installations like Frontier, Aurora, and El Capitan, and with China playing its cards with less transparency, Europe is finally launching its first exascale computer. JUPITER has been installed at the Jülich Supercomputing Center, and it is not going unnoticed: it is coming to train huge AI models, to simulate the atmosphere in great detail and to push forward key research in biomedicine, physics and energy.
What is JUPITER and why does it change the game?

JUPITER stands for Joint Undertaking Pioneer for Innovative and Transformative Exascale Research. It is, as of today, the most powerful supercomputer in Europe and the fourth in the world According to the June 500 Top2025 ranking, entering the exascale league means surpassing the threshold of quintillion operations per second, a magnitude that clearly demonstrates what this system can do in the blink of an eye.
The project has involved a significant investment, 500 million euros co-financed by the European Union and Germany, and is part of the EuroHPC program, which aims to empower high-performance computing on the continent. The ambition is clear: to advance science and industry without depending on third parties.
Where it is and who built it
The machine lives in the Jülich Research Campus, in North Rhine-Westphalia. The location is no coincidence: Jülich has been a supercomputing hub for decades and collaborates with leading scientific networks in Europe.
Several firms have collaborated in the construction and delivery of the system. Eviden (the Atos Group product brand) leads the BullSequana XH3000 architecture Direct liquid cooling; ParTec brings its dynamic modular supercomputing approach; and key technology partners such as NVIDIA and SiPearl join the fold. The result is a facility designed to grow over time through a modular design that facilitates expansion without having to build from scratch.
The system is organized into two large partitions to cover very different scenarios. On the one hand, a GPU-accelerated Booster Module to climb massively parallel applications (ideal for AI and large simulations). On the other hand, a General-purpose Cluster Module with SiPearl Rhea1 processors, the European HPC-oriented chip that provides bandwidth and memory for versatile workloads.
Architecture, size and figures that impress
The heart of JUPITER is powered by the NVIDIA Grace Hopper platform, and in raw numbers we're talking about 24.000 NVIDIA GH200 super chips interconnected. This generation combines CPUs and GPUs on a single superchip to process mountains of data in parallel with an efficiency that's evident in AI training and ultra-high-resolution simulations.
The interconnection is carried out by the NVIDIA Quantum-2 InfiniBand network, with around 51.000 connections in the system, a high-speed spider web designed to allow nodes to communicate with minimal latency and maintain performance when scaling to tens of thousands of processors.
In storage, JUPITER grazes a capacity close to one exabyte, an essential reserve when working with digital twins, kilometer-resolution climate models, or large corpora for multilingual AI. This subsystem is in line with an internal throughput that can move around 2.000 terabytes per second, an astronomical figure that, by way of example, is equivalent to thousands of copies of Wikipedia traveling across the internet in one second.
The installation is modular and has been deployed in 50 specialized containersIn physical space, the size is impressive: a surface comparable to four tennis courts, crisscrossed by more than 260 kilometers of high-capacity cabling so that everything fits together like a Swiss watch.
The maximum electrical consumption is around the 17 megawatts, equivalent to the use of approximately 11.000 residential units. This roof is cushioned by Eviden's direct liquid cooling design, which reduces losses and also allows waste heat to be used to heat buildings on the campus itself.
In terms of effective performance, the European Union stresses that the system aims to up to 90 exaflops in artificial intelligence workloadsThis figure puts the machine in a particularly competitive position for training and fine-tuning foundational models and massive simulations.
To provide an everyday reference, the aggregate power of JUPITER has been compared to the equivalent of about 10 million desktop computers, an image that helps to get an idea of the leap in scale compared to conventional equipment.
Official opening and recognition in rankings
The opening ceremony was held in Jülich on September 5th, with German government officials, European officials, and leading figures from the technology industry. Within this institutional framework, The pioneering nature of the project for Europe was underlined, both for its power and for what it implies in strategic autonomy.
In the Top500 list, JUPITER already appears as the fourth most powerful supercomputer on the planet, behind only El Capitan, Frontier, and Aurora in the United States. Added to this is a clear concern about the environmental impact: the system runs entirely on renewable energy through green supply contracting on the German grid, and its JEDI module has achieved first place in the Green500 of June 2025, which measures energy efficiency in supercomputing.
Energy efficiency that sets the pace
The BullSequana XH3000 architecture not only stretches performance, it also tightens fuel consumption. Thanks to direct liquid cooling, minimizing losses and maintaining the stability of a machine with thousands of nodes that would otherwise require even more energy to dissipate heat. This approach, combined with a renewable power supply, places JUPITER among the elite in terms of efficiency, an increasingly important advantage in data centers of this size.
The role of Jedi module As the leader of the Green500, it is the most visible proof of this commitment. Beyond the medal, it demonstrates that very high-level computing can be scaled without skyrocketing energy bills, and that supercomputing can be an ally in meeting climate goals.
What will be done with Jupiter: science, industry, and public services?
If there's one thing that makes JUPITER stand out, it's its variety of use cases. The machine opens the door to new simulations, the validation of quantum computing proposals, the creation of digital twins, and, of course, train large artificial intelligence models with a European accent and multilingual.
- ClimateECMWF works with kilometer-scale simulations that capture extreme storms and feed the Destination Earth project, which provides digital twins of the planet.
- European AI: The TrustLLM consortium trains language models in multiple European languages for industrial and scientific applications.
- Neuroscience: The Arbor simulator will model the behavior of neurons at the subcellular level, useful for therapies against Alzheimer's and other pathologies.
- Quantum: aims to break the record of 50 qubits in simulation, a step towards practical quantum computing.
- AstrophysicsThe Max Planck Institute is researching cosmic reionization, the stage in which the first stars and galaxies were born.
- Particle Physics: The University of Wuppertal raises the resolution of muon calculations, potentially opening new doors in fundamental physics.
- Video Templates: The University of Munich is exploring compression and diffusion architectures, with applications ranging from medicine to autonomous driving.
- Multimodal models: The University of Lisbon scales open and multilingual models by integrating different fields of science and machine learning.
Beyond that first wave, in Artificial Intelligence The power of the Booster Module will accelerate the development of large multilingual models such as OpenGPT-X, a European initiative that seeks to compete with benchmark proposals in the United States. The climate field, meanwhile, will see improvements in the prediction of extreme events and in the analysis of climate change scenarios with the ICON atmospheric model run at unprecedented resolutions.
En biomedicineThe ability to simulate brain neural networks at the level of individual neurons and create digital twins of organs like the heart opens new avenues for studying neurodegenerative diseases and designing safe treatments for patients. There will also be room to accelerate discoveries in materials science and advance sustainable energy.
Access, calendar and lifespan
JUPITER is part of the EuroHPC network, so any European university, public research center or company You can apply for machine hours. There will be periodic calls twice a year to allocate resources competitively, prioritizing projects with scientific and industrial impact.
There is already real activity. They have started dozens of projectsSome sources mention around thirty active initiatives, while others estimate the number to be over a hundred selected initiatives to be launched in stages. In any case, the flow is constant and allows the infrastructure to be leveraged from day one.
The expected useful life is at least six years, which provides stability to research teams that require continuity and to companies that need to plan developments with realistic deadlines in fields as competitive as AI and scientific simulation.
Europe as a supercomputing hub
With JUPITER up and running, the EuroHPC Joint Undertaking strengthens its ecosystem, which already included machines such as MareNostrum in Spain, LEONARDO in Italy, LUMI in Finland, Discoverer in Bulgaria, MeluXina in Luxembourg, Vega in Slovenia, Karolina in the Czech Republic, and Deucalion in Portugal. The set positions the continent as world power in supercomputing and, above all, provides sovereign capacity for strategic projects.
This approach fits with a priority shared by governments, industry and the research community: sovereign control of data and infrastructureIn practical terms, this means that Europe can train models, run critical simulations, and manage sensitive information without relying on third-country policies.
What the project's protagonists say
Eviden highlights the milestone of delivering the first exascale system in Europe based on its BullSequana XH3000 platform; for the company, it is a step that consolidates its role in the economic and industrial sovereignty of the continent and places the scientific community in its hands. an extraordinary machine made in Europe.
ParTec highlights its dynamic modular architecture, developed together with Jülich and European partners, as the basis for the efficiency and speed that sophisticated AI algorithms demandThe award of the contract, in his opinion, strengthens the competitiveness of German and European suppliers in the construction of supercomputers.
NVIDIA, for its part, highlights that its accelerated computing powers the first European exascale to advance research in Climate and meteorology, materials science, pharmaceutical discoveries, engineering and quantum computing technologies. SiPearl celebrates that its Rhea1 processor is the engine of the Cluster Module and sees this as validation of the European Processor Initiative, with a direct impact on technological sovereignty and reducing the carbon footprint of supercomputing and AI.
JUPITER is not just a display of technical muscle: It is a strategic movement This puts Europe in the exascale league with an efficient, scalable infrastructure open to its scientific and business community. Between the power of the AI Booster Module, the versatility of the Rhea1 Cluster Module, the efficiency leadership of the JEDI module, and a growing EuroHPC ecosystem, the continent is assured of a first-class tool to address climate, health, industrial, and scientific challenges with its own ambition.
Table of Contents
- What is JUPITER and why does it change the game?
- Where it is and who built it
- Architecture, size and figures that impress
- Official opening and recognition in rankings
- Energy efficiency that sets the pace
- What will be done with Jupiter: science, industry, and public services?
- Access, calendar and lifespan
- Europe as a supercomputing hub
- What the project's protagonists say

