Eos NVIDIA DGX SuperPOD
NVIDIA runs Eos, a DGX SuperPOD of 576 DGX H100 systems, as the in-house machine where its own developers train large language models, recommender systems and quantum simulations.
What it runs and how to get time
From the operator- Used for What the operator says the system is used for: science domains, missions or workloads. Taken from the operator, its funder or the system vendor, not from TOP500.
- NVIDIA's internal AI development: large language models, recommender systems, quantum simulations and other large AI workloads 3
Benchmark and hardware
Source per value- Rank Position in the TOP500 edition named in the Edition column. Historic systems keep the rank of the edition where they last appeared.
- 23 1
- Rmax PFLOP/s Measured double-precision LINPACK (HPL) performance of the listed configuration. Older TFLOP/s and GFLOP/s figures are converted to PFLOP/s.
- 121.4 1
- Rpeak PFLOP/s Theoretical peak double-precision performance of the listed configuration. This is not AI or mixed-precision throughput.
- 188.65 1
- HPL efficiency % Rmax divided by Rpeak: the share of theoretical peak the system delivered on LINPACK. Computed from the two sourced figures.
- 64.4 1
- Site Host or operator named by TOP500 for the installation.
- NVIDIA Corporation 1
- Country Country or region reported by TOP500 for the site.
- United States 1
- Region World region of the installation country (grouping applied by this site).
- Americas 1
- Vendor Manufacturer or system supplier exactly as submitted to TOP500.
- Nvidia 1
- Vendor group Supplier grouped for filtering. Bull is the Eviden/Atos line; Other covers single-system suppliers.
- NVIDIA 1
- System model Hardware platform in the cited TOP500 edition.
- NVIDIA DGX H100 1
- Processor CPU description in the cited TOP500 edition; clock and core count refer to the processor model.
- Xeon Platinum 8480C 56C 3.8GHz 1
- Accelerator Accelerator model listed for the system. Empty when TOP500 lists none.
- NVIDIA H100 1
- Accelerator vendor Maker of the accelerator. None listed means TOP500 names no accelerator for the system.
- NVIDIA 1
- Interconnect Network fabric exactly as listed in the cited TOP500 edition.
- Infiniband NDR400 1
- Fabric Interconnect family derived from the listed interconnect (grouping applied by this site).
- InfiniBand 1
- Cores cores Total cores submitted to TOP500, including accelerator cores where TOP500 counts them. Not a CPU-only count and not a CUDA-core count.
- 485,888 1
- Installed Installation year reported in the TOP500 system record. Not necessarily the year of production acceptance.
- 2023 2
- Edition TOP500 edition (YYYY-MM) that supplies the ranking and benchmark data. A historic edition does not assert current operating status.
- 2026-06 1
- OS Operating system from the TOP500 system record.
- Ubuntu 22.04.3 LTS 2
- TOP500 record Link to the TOP500 database record for this exact submission.
- https://www.top500.org/system/180239/ 2
Sources
- TOP500 list, June 2026 accessed 2026-11-11
- TOP500 system record accessed 2026-11-11
- NVIDIA Eos Revealed: Peek Into Operations of a Top 10 Supercomputer | NVIDIA Blog accessed 2026-11-11