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

50

x

MORE AI FACTORY
OUTPUT*

50

x

Up to a 50X increase in AI factory output for reasoning-model inference compared to Hopper platforms, combining higher throughput and lower latency for maximum token revenue.

10

x

BETTER LATENCY
(TPS / USER)*

10

x

Up to 10X boost in user responsiveness (tokens per second per user) compared to Hopper platforms, enabling faster, more responsive interactive AI experiences.

40

TB

COHERENT FAST
MEMORY PER RACK*

40

TB

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

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 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.

Every founder in AI should work with Crusoe. They move as fast as a small startup, but provide the robust, scaled infrastructure necessary to serve a real-time model to hundreds of thousands of happy users.

Oliver Cameron

CEO

Windsurf's NVIDIA H100 Tensor Core GPUs on Crusoe have been incredibly reliable with a cluster uptime of 99.98%.

Varun Mohan

Co-Founder & CEO

Crusoe has been an outstanding partner from the get-go - all of our in-house machine learning models have been trained on Crusoe Cloud. They provide a level of quality of service, responsiveness, and support for early access programs that we couldn't find with any other cloud provider.

Prasanth Veerina

Co-Founder

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

NVIDIA GB300NVL72