NVIDIA HGX H100 8-GPU

baseboard
8× H100
NVSwitch + NVLink
2022
FP64
0.3
PFLOPS
FP32
0.5
PFLOPS
Power
8.0
kW Total
Memory
640
GB Total

HGX H100 8-GPU configuration for hyperscalers

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

Systems built on this design

2 configurations

NVIDIA HGX H100 8-GPU is the baseboard. The systems above are OEM implementations of it and share its accelerator performance; they differ in chassis, CPU, memory and cooling.

FP64
0.27
PFLOPS
34.0 TFLOPS/kW
FP32
0.54
PFLOPS
67.0 TFLOPS/kW
TF32
3.96
PFLOPS
989.0 TFLOPS/kW
FP16
7.92
PFLOPS
1979.0 TFLOPS/kW

System Details

GPU Configuration

GPU Count: 8 GPUs
Architecture: Hopper
Interconnect: NVSwitch + NVLink

System Specifications

Form Factor: baseboard
Total Power: 8.0 kW
Total Memory: 640 GB
Memory Bandwidth: 26.8 TB/s

Precision Performance Breakdown

PrecisionSystem PerformancePer GPUEfficiency
0.272 PFLOPS 34.0 TFLOPS 34.0 TFLOPS/kW
0.536 PFLOPS 67.0 TFLOPS 67.0 TFLOPS/kW
3.956 PFLOPS 494.5 TFLOPS 989.0 TFLOPS/kW
7.916 PFLOPS 989.5 TFLOPS 1979.0 TFLOPS/kW
7.916 PFLOPS 989.5 TFLOPS 1979.0 TFLOPS/kW
15.832 PFLOPS 1979.0 TFLOPS 3958.0 TFLOPS/kW
15.832 PFLOPS 1979.0 TFLOPS 3958.0 TFLOPS/kW

Where a vendor states a basis, the figure shown is the dense one, and any figure it publishes is listed separately. Vendors commonly headline the sparse number instead: for NVIDIA's 2:4 structured sparsity that is exactly twice the dense figure, though other vendors' sparse modes do not all follow that ratio.

Powered by NVIDIA H100

This system utilizes 8 × NVIDIA H100 SXM5 80GB GPUs, each delivering exceptional performance for AI and HPC workloads.

Per GPU TDP

700W

Per GPU Memory

80 GB

Process Node

4nm

Architecture

Hopper

Documentation & Resources

Flopper Spec Sheet

NVIDIA HGX H100 8-GPU specifications, generated from our database. Printable.

Vendor product page

NVIDIA HGX H100 8-GPU documentation

View ↗

workstation-datasheet-dgx-spark-gtc25-spring-nvidia-us-3716899-web.pdf

NVIDIA • 2025-10-16

View Document ↗

NVIDIA DGX Documentation

System guides, deployment resources

Browse ↗

Typical Use Cases

Large Language Model Training
Distributed Deep Learning
Multi-GPU Inference
HPC Simulations
Scientific Computing

The NVIDIA HGX H100 8-GPU runs 8× H100 GPUs over NVSwitch + NVLink, delivering 15.8 PFLOPS FP8 dense.