HP

HPE Cray XD670

rack
8× H200
NVIDIA NVLink with NVSwitch across the eight SXM modules
2024
FP64
0.3
PFLOPS
FP32
0.5
PFLOPS
Power
kW Total
Memory
1155
GB Total

A 5U server carrying eight NVIDIA H200 SXM GPUs at 700 W each with 141 GB of HBM3e apiece, driven by a single two-socket node of 5th generation Intel Xeon Scalable processors at up to 400 W, with 32 DDR5 DIMMs across eight channels per socket at up to 5,600 MHz. It is air cooled with a direct liquid cooling option. HPE has taken six first-place results with it in MLPerf Inference v5.1, including computer vision and LLM chat and text generation. Two things this row deliberately does not claim: HPE describes the GPUs only as "8x NVIDIA H200 SXM" and never names the HGX baseboard, though eight H200 SXM at 700 W is precisely the HGX H200 8-GPU configuration, and the compute figures shown are NVIDIA's for that baseboard rather than any HPE claim; and HPE publishes component TDPs but no system power figure, so total power is left blank rather than summing 8 x 700 W and 2 x 400 W, which would count silicon only and understate the machine. Part numbers are also not recorded, since none appears on HPE's page.

We will point you at suppliers who have it. Free, and no signup.

FP64
0.27
PFLOPS
FP32
0.54
PFLOPS
TF32
3.96
PFLOPS
FP16
7.92
PFLOPS

System Details

GPU Configuration

GPU Count: 8 GPUs
Architecture: Hopper
Interconnect: NVIDIA NVLink with NVSwitch across the eight SXM modules

System Specifications

Form Factor: rack
Total Power:
Total Memory: 1155 GB
Memory Bandwidth: 38400 GB/s

Precision Performance Breakdown

PrecisionSystem PerformancePer GPUEfficiency
0.272 PFLOPS 34.0 TFLOPS
0.536 PFLOPS 67.0 TFLOPS
3.956 PFLOPS 494.5 TFLOPS
7.916 PFLOPS 989.5 TFLOPS
7.916 PFLOPS 989.5 TFLOPS
15.832 PFLOPS 1979.0 TFLOPS
15.832 PFLOPS 1979.0 TFLOPS

All figures are dense. Vendors commonly headline the number, which is twice the dense one.

Powered by NVIDIA H200

This system utilizes 8 × NVIDIA H200 SXM 141GB GPUs, each delivering exceptional performance for AI and HPC workloads.

Per GPU TDP

700W

Per GPU Memory

141 GB

Process Node

4nm

Architecture

Hopper

Documentation & Resources

Official Datasheet

HPE Cray XD670 technical specifications

Download PDF

HPE Compute XD690 QuickSpecs (a50009220enw, V6)

HPE • 2026-07-06

View Document ↗

Typical Use Cases

AI/ML Training
High-Performance Computing
Data Analytics

The HPE Cray XD670 runs 8× H200 GPUs over NVIDIA NVLink with NVSwitch across the eight SXM modules, delivering 15.8 PFLOPS FP8 dense.