NVIDIA HGX B100 8-GPU
baseboard
8× B100
NVSwitch + NVLink
2024
FP64
0.2
PFLOPS
FP32
0.5
PFLOPS
Power
5.6
kW Total
Memory
1573
GB Total
FP64
0.24
PFLOPS
FP32
0.48
PFLOPS
TF32
7.00
PFLOPS
FP16
14.00
PFLOPS
System Details
GPU Configuration
GPU Model: NVIDIA
B100
SXM 192GB
GPU Count: 8 GPUs
Architecture: Blackwell
Interconnect: NVSwitch + NVLink
System Specifications
Form Factor: baseboard
Total Power: 5.6 kW
Total Memory: 1573 GB
Memory Bandwidth: 64000 GB/s
Precision Performance Breakdown
| Precision | System Performance | Per GPU | Efficiency |
|---|---|---|---|
| FP64 | 0.240 PFLOPS | 30.0 TFLOPS | — |
| FP32 | 0.480 PFLOPS | 60.0 TFLOPS | — |
| TF32 | 7.000 PFLOPS | 875.0 TFLOPS | — |
| FP16 | 14.000 PFLOPS | 1750.0 TFLOPS | — |
| BF16 | 14.000 PFLOPS | 1750.0 TFLOPS | — |
| FP8 | 28.000 PFLOPS | 3500.0 TFLOPS | — |
| FP4 | 56.000 PFLOPS | 7000.0 TFLOPS | — |
| INT8 | 28.000 PFLOPS | 3500.0 TFLOPS | — |
Powered by NVIDIA B100
This system utilizes 8 × NVIDIA B100 SXM 192GB GPUs, each delivering exceptional performance for AI and HPC workloads.
Per GPU TDP
700W
Per GPU Memory
192 GB
Process Node
4nm
Architecture
Blackwell
Documentation & Resources
workstation-datasheet-dgx-spark-gtc25-spring-nvidia-us-3716899-web.pdf
NVIDIA • 2025-10-16
NVIDIA DGX Documentation
System guides, deployment resources
Typical Use Cases
Large Language Model Training
Distributed Deep Learning
Multi-GPU Inference
HPC Simulations
Scientific Computing
The NVIDIA HGX B100 8-GPU with 8× B100 GPUs is designed for enterprise-scale workloads requiring 0.2 PFLOPS of compute power with NVSwitch + NVLink interconnect for efficient multi-GPU communication.