NVIDIA Vera Rubin NVL72

rack
72× Rubin
NVLink 6 / NVSwitch
2026
FP64
2.4
PFLOPS
FP32
9.4
PFLOPS
Power
kW Total
Memory
20736
GB Total

Rack-scale system pairing 72 Rubin GPUs with 36 Vera CPUs (3,168 Olympus Arm cores total, 54 TB LPDDR5X CPU memory). Headline NVFP4 inference 3,600 PFLOPS dense; NVFP4 training 2,520 PFLOPS dense. Tensor-core-emulated FP32 SGEMM reaches 28.8 PFLOPS, FP64 DGEMM 14.4 PFLOPS. Aggregate memory shown is HBM4 only (CPU LPDDR5X is excluded from GPU memory aggregate). Total chips per rack: 1,296. Specifications preliminary per NVIDIA GTC 2025 footnote.

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

Systems built on this design

1 configuration

NVIDIA Vera Rubin NVL72 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
2.40
PFLOPS
FP32
9.36
PFLOPS
TF32
144.00
PFLOPS
FP16
288.00
PFLOPS

System Details

GPU Configuration

GPU Model: NVIDIA Rubin SXM
GPU Count: 72 GPUs
Architecture: Rubin
Interconnect: NVLink 6 / NVSwitch

System Specifications

Form Factor: rack
Total Power:
Total Memory: 20.7 TB
Memory Bandwidth: 1.6 PB/s

Precision Performance Breakdown

PrecisionSystem PerformancePer GPUEfficiency
2.400 PFLOPS 33.3 TFLOPS
9.360 PFLOPS 130.0 TFLOPS
144.000 PFLOPS 2000.0 TFLOPS
288.000 PFLOPS 4000.0 TFLOPS
288.000 PFLOPS 4000.0 TFLOPS
1260.000 PFLOPS 17500.0 TFLOPS
18.000 PFLOPS 250.0 TFLOPS
2520.000 PFLOPS 35000.0 TFLOPS
FP6 1260.000 PFLOPS 17500.0 TFLOPS
28.800 PFLOPS 400.0 TFLOPS
14.400 PFLOPS 200.0 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 Rubin

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

Per GPU TDP

Per GPU Memory

288 GB

Process Node

Architecture

Rubin

Documentation & Resources

Flopper Spec Sheet

NVIDIA Vera Rubin NVL72 specifications, generated from our database. Printable.

Vendor product page

NVIDIA Vera Rubin 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 Vera Rubin NVL72 runs 72× Rubin GPUs over NVLink 6 / NVSwitch, delivering 1.26 EFLOPS FP8 dense.