NVIDIA DGX GB300 NVL72

rack
72× B300
NVLink + NVSwitch
2025
FP64
0.1
PFLOPS
FP32
6.0
PFLOPS
Power
kW Total
Memory
20736
GB Total

36 GB300 superchips (72 B300 GPUs + 36 Grace CPUs) in liquid-cooled rack

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

FP64
0.10
PFLOPS
FP32
6.00
PFLOPS
TF32
90.00
PFLOPS
FP16
180.00
PFLOPS

System Details

GPU Configuration

GPU Count: 72 GPUs
Architecture: Blackwell Ultra
Interconnect: NVLink + NVSwitch

System Specifications

Form Factor: rack
Total Power:
Total Memory: 20.7 TB
Memory Bandwidth: 576 TB/s

Precision Performance Breakdown

PrecisionSystem PerformancePer GPUEfficiency
0.100 PFLOPS 1.4 TFLOPS
6.000 PFLOPS 83.3 TFLOPS
90.000 PFLOPS 1250.0 TFLOPS
180.000 PFLOPS 2500.0 TFLOPS
180.000 PFLOPS 2500.0 TFLOPS
360.000 PFLOPS 5000.0 TFLOPS
1080.000 PFLOPS 15000.0 TFLOPS
12.000 PFLOPS 166.7 TFLOPS
FP6 360.000 PFLOPS 5000.0 TFLOPS

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 B300

This system utilizes 72 × NVIDIA B300 SXM 288GB GPUs, each delivering exceptional performance for AI and HPC workloads.

Per GPU TDP

1400W

Per GPU Memory

288 GB

Process Node

4nm

Architecture

Blackwell Ultra

Documentation & Resources

Flopper Spec Sheet

NVIDIA DGX GB300 NVL72 specifications, generated from our database. Printable.

Vendor product page

NVIDIA DGX GB300 NVL72 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

AI/ML Training
High-Performance Computing
Data Analytics

The NVIDIA DGX GB300 NVL72 runs 72× B300 GPUs over NVLink + NVSwitch, delivering 360 PFLOPS FP8 dense.