NVIDIA GB300
NVL72

Name: NVIDIA GB300 NVL72
Brand: NVIDIA
Price: Contact Sales
Availability: InStock

The NVIDIA GB300 NVL72 is a liquid-cooled, rack-scale system that unifies 72 NVIDIA Blackwell Ultra GPUs and 36 Arm-based NVIDIA Grace CPUs into a single platform built for test-time scaling and AI reasoning.

Contact sales

View pricing

Rack-scale performance for AI reasoning

50

x

MORE AI FACTORY
OUTPUT*

50

x

MORE AI FACTORY
OUTPUT*

Up to a 50x increase in AI factory output for reasoning-model inference compared to an NVIDIA H100 Tensor Core GPU, combining higher throughput and lower latency for maximum token revenue.

10

x

BETTER LATENCY
(TPS / USER)*

10

x

BETTER LATENCY
(TPS / USER)*

Up to 10x boost in user responsiveness (tokens per second per user) compared to an NVIDIA H100 Tensor Core GPU, enabling faster, more responsive interactive AI experiences.

40

TB

COHERENT FAST
MEMORY PER RACK

40

TB

COHERENT FAST
MEMORY PER RACK

Up to 40TB of coherent fast memory across 72 Blackwell Ultra GPUs and 36 Grace CPUs, including up to 21TB of HBM3E, so trillion-parameter models and long-context reasoning stay resident in a single NVLink domain.

30

x

FASTER REAL-TIME
VIDEO GENERATION*

30

x

FASTER REAL-TIME
VIDEO GENERATION*

Up to 30x faster real-time video generation than Hopper for world foundation models and physical AI such as robotics and autonomous vehicles.

*Compared to NVIDIA H100 Tensor Core GPU

Ideal workloads for the NVIDIA GB300 NVL72

AI reasoning & agentic AI

Purpose-built for test-time scaling, in which models reason through complex queries during inference. The 72-GPU NVLink domain powers agentic systems that plan, take action, and solve multistep problems at scale.

Real-time video generation & world simulation

Generate real-time, photo-realistic video from world foundation models like NVIDIA Cosmos, and 3D world simulators for physical AI applications such as robotics and autonomous vehicles.

Large-scale inference & data processing

Unified memory and low-latency interconnects supercharge trillion-parameter inference and large-context reasoning. Blackwell’s Decompression Engine accelerates database queries and real-time data processing.

Build the future faster with Crusoe Cloud

Up to 20 times faster and 81% less expensive than traditional cloud providers.

Unparalleled performance

Scale ambitiously and fearlessly knowing your AI workloads are backed by peerless infrastructure.

Accelerated breakthroughs

Focus on innovation not infrastructure with intuitive, AI-native systems designed to keep you building.

Abundant compute

Achieve your AI potential with vast compute and energy resources.

Crusoe provides the latest NVIDIA hardware, extraordinary support, and overall a great partner to enable our data, training, and inference infrastructure. Crusoe is consistently accommodating to our needs and is not afraid to dive deep in helping us solve hard problems.

Philip Petrakian

Member of Technical Staff

This was not tens of nodes or hundreds of nodes, but thousands of nodes on extremely short notice. I remember being on the call with Crusoe late evening Friday night, Saturday morning, trying to figure out the best way to get this capacity. We were able to strike a deal within a couple of days, and we got those nodes up and running within a few hours of signing.

Chenyu Zhao

Co-Founder

There are a lot of providers selling GPUs out there, but ultimately the GPU is most useful when it's backed by reliable infrastructure. We've had good success with Crusoe: the network fabric is very performant, and we're able to pump a lot of gigabits on a constant basis.

Sachin Agarwal

ML Infrastructure & Security Engineering Lead

We benchmarked the cluster, and we realized that Crusoe matches the state-of-the-art speed in terms of both the GPUs and the storage. We decided to go with Crusoe because it was the best possible choice.

David Novotný

Co-Founder + CTO

NVIDIA GB300
NVL72

Rack-scale performance for AI reasoning

Ideal workloads for the NVIDIA GB300 NVL72