NVIDIA GB300 NVL72

Manufacturer specification reference

Architecture

Grace Blackwell UltraNVIDIA GB300 NVL72 (external source) · NVIDIA Blackwell Ultra datasheet (external source) · NVIDIA Vera Rubin POD: Seven Chips, Five Rack-Scale Systems, One AI Supercomputer (external source) · CUDA GPU Compute Capability (external source)

Category

Complete rack-scale referenceNVIDIA GB300 NVL72 (external source) · NVIDIA Blackwell Ultra datasheet (external source) · NVIDIA Vera Rubin POD: Seven Chips, Five Rack-Scale Systems, One AI Supercomputer (external source) · CUDA GPU Compute Capability (external source)

Accelerator memory

20,000 GBPublished rounded 20 TB aggregate GPU memory converted to decimal GB; excludes CPU LPDDR5X.NVIDIA GB300 NVL72 (external source)

Memory type

HBM3eNVIDIA Blackwell Ultra datasheet (external source)

Memory bandwidth

576 TB/sUp to rack aggregate GPU memory bandwidth, not NVLink bandwidth.NVIDIA GB300 NVL72 (external source)

Power

Not verified for this recordTotal rack operating draw not verified in the reviewed sources; individual GPU TDP is not rack power.NVIDIA GB300 NVL72 (external source) · NVIDIA Blackwell Ultra datasheet (external source) · NVIDIA Vera Rubin POD: Seven Chips, Five Rack-Scale Systems, One AI Supercomputer (external source) · CUDA GPU Compute Capability (external source)

Precision formats

FP4, FP8, FP6, INT8, FP16, BF16, TF32, FP32, FP64NVIDIA GB300 NVL72 (external source)

Cooling / integration

Fully liquid-cooled rack-scale architecture.NVIDIA GB300 NVL72 (external source) · NVIDIA Blackwell Ultra datasheet (external source) · NVIDIA Vera Rubin POD: Seven Chips, Five Rack-Scale Systems, One AI Supercomputer (external source) · CUDA GPU Compute Capability (external source)

Configuration boundaries

• GPU memory and CPU memory are separate. Fast memory on the product page includes both.
• Rack totals are manufacturer-published rounded figures; no inferred per-GPU memory value is supplied.

Published arithmetic throughput

Deployment considerations

• Verify CPU/GPU software architecture assumptions and end-to-end serving topology.
• Use measured workload power and OEM site-planning documentation before calculating facility capacity.

Software ecosystem

CUDA · NVIDIA Mission Control · NVIDIA AI Enterprise. Confirm the exact model, runtime release, server integration and vendor support matrix before evaluating a deployment.