Supercomputers/Systems/Sofia (VSC Tier-1)
Belgium · operational · mixed
Sofia (VSC Tier-1)
Also known as sofia
Operated by Flemish Supercomputer Centre at Nexus Data Center, Research Park Zellik .
Researched with AI assistance, checked by scripts. These rows were researched by AI agents reading public operator, laboratory and vendor sources, appended by scripts and checked by automated validation; no subject-matter expert has reviewed them (how this site is made). A mechanical second-reader pass has since fetched every cited source: 1350 of 1581 systems have a readable citation that names them, and 64 are genuinely weakly sourced. Every claim carries its source and a confidence tier. Treat anything below verified as a lead, not a citation.
Measured performance
- Rmax
- 8.19 PFlop/s
- Rpeak
- 12.17 PFlop/s
- Rmax ÷ Rpeak
- 67.3%
- Cores
- 27,456
- Power
- 164.66 kW
- Per watt
- 49.7 GF/W
Figures are as last publicly reported for the configuration described below, not a live measurement. Where a system was upgraded in place, the post-upgrade configuration is shown and the earlier one appears in the timeline.
How it compares
Ranked against the other machines in this dataset that report the same figure: those that first came into service within two years of Sofia (VSC Tier-1), and those in Belgium. Computed from our tables; a metric is ranked only when at least eight peers report it.
| Metric | Value | Against its era | Against its country |
|---|---|---|---|
| Rmax | 8.19 PFlop/s | #104 of 158 · bottom 35% | - |
| Energy efficiency | 49.7 GF/W | #38 of 81 · top 46% | - |
| Rmax ÷ Rpeak | 67.3 % | #100 of 155 · bottom 37% | - |
| Power draw | 165 kW | #62 of 85 · bottom 28% | - |
Every metric is ranked largest-first, so a high power-draw rank means a big power draw, not a good one. Rmax ÷ Rpeak uses HPL-measured results only. Rankings move as machines are added; they describe this dataset, not the world.
What this machine is made of
One row per supplier relationship. “Supplier at build” is the company that shipped the part at the time; where that company has since been acquired, the parent it rolls up to today is shown beside it. That distinction is what makes ticker-level aggregation possible across a thirty-year dataset.
| Role | Part | Supplier at build | Quantity | Confidence | Source |
|---|---|---|---|---|---|
| Integrator | - NEC HGX H200 system | NEC | - | Reported | top500.org |
| Accelerator | NVIDIA H200 SXM Accelerators CUDA (Hopper GH100) · 16,896C · 1.98 GHz · TSMC 4N · 700 W NVIDIA H200 SXM5 141 GB | NVIDIA | - | Reported | top500.org |
| CPU | AMD EPYC 9004 (Genoa) CPUs x86-64 · 96C · 2.4 GHz · TSMC N5 · 360 W AMD EPYC 9654 96C 2.4 GHz | AMD | - | Reported | top500.org |
| Interconnect | NVIDIA InfiniBand NDR (Quantum-2) Interconnect Fat tree or dragonfly+ · 400 Gb/s per port · Under 0.6 microseconds InfiniBand NDR400 | NVIDIA | - | Reported | top500.org |
| Operating system | Rocky Linux Operating systems RHEL-compatible Linux, community-maintained · Downstream rebuild of Red Hat Enterprise Linux source Rocky Linux | Rocky Enterprise Software Foundation | - | Reported | top500.org |
The read
Flanders' new Tier-1 supercomputer of the Flemish Supercomputer Center, hosted by the Vrije Universiteit Brussel at the Nexus data center in Research Park Zellik. VSC announced on 23 June 2026 a debut at 222nd on the TOP500 and 41st on the Green500, with the first academic projects starting on 3 July 2026 for AI, climate, health, engineering and other fields. The machine was bought with an 8.6 million euro Research Foundation Flanders (FWO) investment funded by the Flemish Government, runs on renewable electricity, uses rainwater for cooling where possible and reuses waste heat to warm buildings in the Research Park. TOP500 (list full for our table, so no list row) lists an NEC HGX H200 system with AMD EPYC 9654 96C 2.4 GHz, NVIDIA H200 SXM5 141 GB, InfiniBand NDR400 and Rocky Linux, 27,456 cores, Rmax 8.19 and Rpeak 12.17 PFlop/s, 164.66 kW (129.57 kW in an optimized run reaching 7.00 PFlop/s) and HPCG 122.0 TFlop/s. VSC's article does not give node or GPU counts.
Site & facility
Change history
- 2026-10-17 Added Sofia (VSC Tier-1)
Nearby in scale
The machines closest to Sofia (VSC Tier-1) by Rmax, smaller to larger.
Related systems
Same operator
Same accelerator
- ASPIRE 2B (GPU Partition) · Singapore, operational, 2026
- Cassava AI Factory · South Africa, operational, 2026
- EYAS · Saudi Arabia, operational, 2026
- LiDO4 · Germany, operational
- Maximus-02 · USA, operational, 2026
- Nanyang Titan · Singapore, operational, 2026
Source check
We fetched this system's own citations and recorded whether each page actually mentions it. This is a corroboration signal, not a fact check, and it is published so you can see how well the sourcing holds up rather than take it on trust.
| Cited source | Result | Found on the page |
|---|---|---|
| top500.org | names system and part | NVIDIA H200 SXM, AMD EPYC 9004 (Genoa), NVIDIA InfiniBand NDR (Quantum-2), Rocky Linux |
| vscentrum.be | names system only | - |
Checked 2026-10-18 by pnpm verify. Re-run it and the table changes with the web.
Further reading
Operating a supercomputer
Acceptance testing, why "installed" and "in production" are six months apart, and the machine lifecycle.
Inside a node
Why accelerators exist, what the memory hierarchy costs, and how the CPU and accelerator merged onto one package.
The interconnect
Topologies, why latency and tail behaviour matter more than bandwidth, and how the fabric market consolidated.