One unit. Maximum scaling.

A rack as a supercomputer.

With the NVL72 platform, NVIDIA brings a complete rack-scale solution for training, inference and AI reasoning. The systems combine state-of-the-art Grace CPUs with Blackwell GPUs and deliver the highest computing power with maximum efficiency. The NVL72 combines 72 GPUs and 36 Grace CPUs into a single computing domain. Thanks to NVLink and liquid cooling, the entire rack operates as a single, high-performance GPU. This means that even models with trillions of parameters can be trained and made available in real time.

Suitable for every AI workload.From LLM training to the AI Factory.
Suitable for every AI workload.

Suitable for every AI workload.

From LLM training to the AI Factory.

  • GB200 NVL72: For training and inference of large language models, optimised for established workloads with maximum energy efficiency.

  • GB300 NVL72: For AI factories and reasoning, with 40 TB fast memory and higher throughput per megawatt. Ideal for companies with the highest demands on scaling and speed.

Which NVL72 suits your project?

Comparison of the two platforms at a glance.

Feature

GB300 NVL721

GB200 NVL72

Configuration

36 Grace CPU: 72 Blackwell Ultra GPUs

36 Grace CPU: 72 Blackwell GPUs

FP4 tensor computing unit

1.400 | 1,100² PFLOPS

1.440 PFLOPS

FP8/FP6 tensor computing unit

720 PFLOPS

720 PFLOPS

INT8 tensor computing unit23 POPS720 POPS

FP16/BF16 tensor computing unit

360 PFLOPS

360 PFLOPS

FP32 Tensor computing unit6 PFLOPS

5.760 TFLOPS

FP64 Tensor computing unit100 TFLOPS2.880 TFLOPS

GPU memory | bandwidth

Up to 21 TB | Up to 576 TB/s

Up to 13.5 TB HBM3e | 576 TB/s

NVLink bandwidth

130 TB/s

130 TB/s

Number of CPU compute units

2.592 Arm® Neoverse V2 computing units

2.592 Arm® Neoverse V2 compute units

CPU memory | bandwidth

Up to 18 TB SOCAMM with LPDDR5X | Up to 14.3 TB/s

Up to 17 TB LPDDR5X | Up to 18.4 TB/s

1. Preliminary technical data. Subject to change without notice. All technical data for Tensor computing units are with sparsity unless otherwise stated.

2. Without sparsity.

3. With low data density.

From rack to cluster:
NVIDIA SuperPOD.
NVL72 as a building block for AI supercomputers.
From rack to cluster: NVIDIA SuperPOD.

From rack to cluster:
NVIDIA SuperPOD.

NVL72 as a building block for AI supercomputers.

Several NVL72 racks can be connected via NVLink to form an NVIDIA SuperPOD - a complete AI infrastructure at data centre level. This creates scalable systems that provide ExaFLOP performance for research and industry.

Technological breakthroughs with NVIDIA Blackwell

AI Reasoning & Inference

Test-time scaling and AI reasoning increase the computing requirements to ensure quality and throughput. The tensor cores of the NVIDIA Blackwell GPUs - in the GB300 NVL72 with Blackwell Ultra - offer up to twice the attention layer acceleration and up to 1.5× more AI FLOPS compared to the previous generation.

Up to 288 GB HBM3e

A larger memory enables larger batch sizes and maximum throughput performance. The Blackwell GPUs in the GB200 and GB300 NVL72 utilise HBM3e - in the Ultra version with up to 288 GB per GPU for particularly long context lengths and maximum efficiency.

NVIDIA Blackwell architecture

The NVIDIA Blackwell architecture sets new standards in accelerated computing. It enables a new era of performance, efficiency and scaling - the foundation of both NVL72 platforms.

NVIDIA ConnectX-8 SuperNIC

With the NVIDIA ConnectX-8 SuperNIC, an I/O module with 800 Gb/s per GPU is available for the GB300 NVL72. Together with NVIDIA Quantum-X800 InfiniBand or Spectrum-X Ethernet, the NVL72 achieves top values in Remote Direct Memory Access (RDMA) and workload efficiency.

NVIDIA Grace CPU

The NVIDIA Grace CPU is the link between GPUs and memory in both NVL72 platforms. It combines outstanding performance and high memory bandwidth with twice the energy efficiency of conventional server processors.

Fifth generation NVIDIA NVLink

Seamless GPU-to-GPU communication is crucial for accelerated computing. With NVLink Gen 5, the NVL72 achieves up to 1.8 TB/s bandwidth per GPU and connects all components to a common computing domain.

First step

Get in touch now!

Rely on the best AI infrastructure on the market

With the NVIDIA GB200 NVL72 & GB300 NVL72, you get the technology that the world's leading companies and research institutions are already using successfully. Let's work together to realise your AI vision and prepare your company for the future.

Contact sysGen today and find out how NVIDIA GB200 NVL72 & GB300 NVL72 can revolutionise your AI strategy. Together we can put your AI projects in the fast lane!

Contact Details
Additional Information

Frequently asked questions about NVL72.

NVIDIA Omniverse provides a powerful platform for the development and management of 3D content and simulations. With advanced technologies such as OpenUSD and RTX rendering, companies can significantly improve their design and simulation processes. sysGen supports you with customised hardware solutions, software integration and comprehensive consulting to take full advantage of Omniverse and optimise your 3D workflows.

Discover suitable solutions

NVIDIA SuperPOD

From a single NVL72 rack to a complete AI supercomputer.

NVIDIA DGX & HGX systems

AI computing power in a compact format - as a building block or entry into the NVIDIA infrastructure.

NVIDIA AI For Enterprise

From a single NVL72 rack to a complete AI supercomputer.

Ihre optimale Website-Nutzung

Diese Website verwendet Cookies und bindet externe Medien ein. Mit dem Klick auf „✓ Alles akzeptieren“ entscheiden Sie sich für eine optimale Web-Erfahrung und willigen ein, dass Ihnen externe Inhalte angezeigt werden können. Auf „Einstellungen“ erfahren Sie mehr darüber und können persönliche Präferenzen festlegen. Mehr Informationen finden Sie in unserer Datenschutzerklärung.

Detailinformationen zu Cookies & externer Mediennutzung

Externe Medien sind z.B. Videos oder iFrames von anderen Plattformen, die auf dieser Website eingebunden werden. Bei den Cookies handelt es sich um anonymisierte Informationen über Ihren Besuch dieser Website, die die Nutzung für Sie angenehmer machen.

Damit die Website optimal funktioniert, müssen Sie Ihre aktive Zustimmung für die Verwendung dieser Cookies geben. Sie können hier Ihre persönlichen Einstellungen selbst festlegen.

Noch Fragen? Erfahren Sie mehr über Ihre Rechte als Nutzer in der Datenschutzerklärung und Impressum!

Ihre Cookie Einstellungen wurden gespeichert.