Supermicro GB300 NVL72 Rack-Scale AI System

The Supermicro GB300 NVL72 is a flagship rack-scale AI system for large-scale training and inference in AI factories and HPC environments. Its liquid-cooled design and integrated Blackwell Ultra platform provide the headroom needed for frontier models and heavier multi-rack workloads.

Supermicro GB300 NVL72 Key Platform Specifications

  • Primary Use Case: Large-Scale AI Training & Inference
Submit an enquiry for pricing
SKU SRS-GB300-NVL72 Categories , , Brand:

Supermicro GB300 NVL72 Overview

As frontier AI models grow in size and traffic, infrastructure teams need rack-level capacity that keeps pace with memory demand, interconnect pressure, and dense power and cooling requirements.

Rack-Scale AI Infrastructure for Demanding Workloads

The Supermicro GB300 NVL72 is a rack-scale platform for the largest AI training and inference environments, designed for production deployments that need a single, integrated system for very large models and heavy multi-rack workloads.

Designed to Support Capacity and Scale-Up Headroom

With up to 72 GPUs per server, 288 GB of GPU memory, 5th Gen NVLink, and 800G maximum port speed, it provides the connectivity and capacity profile needed to keep large models moving efficiently across the rack.

Operational Fit for Expanding AI Programmes

That makes it a practical fit when teams want more room for larger contexts, less workload partitioning, and a clearer path for scaling AI programmes without reaching infrastructure limits as quickly.

For a closer look at the Supermicro GB300 NVL72, our team can help assess where it fits within your AI infrastructure plan.

Supermicro GB300 NVL72 Key Features​

Supermicro GB300 NVL72 is a server platform for high-density AI and accelerated computing environments, built to support large-scale deployment with an architecture focused on performance, integration, and operational consistency.

High-Density AI Compute Platform

Dense GPU Architecture
The platform is designed to consolidate accelerated workloads in a single server environment with support for up to 72 GPUs.

Large-Scale Memory Capacity
It provides 288 GB of GPU memory to support data-intensive AI and compute workflows.

High-Speed Interconnect Fabric
The system is built for fast data movement across the platform with maximum port speed support of 800G.

Integrated Workload Consolidation
Its architecture is suited to reducing fragmentation by hosting demanding accelerated workloads within one coordinated server design.

Operational Control At Scale

Platform-Level Consistency
The server architecture is intended to deliver a consistent operating model across deployed systems for enterprise infrastructure planning.

Accelerated Workload Alignment
The design aligns compute density and memory capacity to support demanding AI processing requirements in a single platform.

Deployment Flexibility
The platform can be used across new and refurbished configurations while remaining centered on the same server role and architecture.

Speak to a Supermicro Server Specialist

If you are planning dense AI infrastructure or consolidating accelerated workloads, our team can help map Supermicro GB300 NVL72 into a server strategy aligned to your performance targets.

Supermicro GB300 NVL72 Technical Specifications

Full specifications for this model are listed below.

Additional information

Product Family

Supermicro Rack Scale

Product Family

Supermicro Rack Scale

Product Series

GB300 NVL72

Device Type

Rack-Scale AI System

Deployment

AI Factory / HPC

Product Series

GB300 NVL72

Target Organisation Size

Hyperscaler

Deployment

AI Factory / HPC

Primary Use Case

Large-Scale AI Training & Inference

Target Organisation Size

Hyperscaler

Product Tier

Flagship

Primary Use Case

Large-Scale AI Training & Inference

PCIe Generation

Gen5

Product Tier

Flagship

Form Factor

48U Rack-Scale

Host Interface

NVLink-C2C / NVLink

Device Type

Rack-Scale AI System

PCIe Generation

Gen5

Host Interface

NVLink-C2C / NVLink

Network Protocols

InfiniBand / Ethernet

Network Protocols

InfiniBand / Ethernet

Form Factor

48U Rack-Scale

Maximum Port Speed

800G

Maximum Port Speed

800G

RDMA Support

Yes

RoCE Support

Yes

GPUDirect Support

Yes

Evaluating whether this is the right fit for your environment?

Our specialists are here to help assess compatibility, compare suitable alternatives, or talk through your configuration needs before committing to a solution.

Contact us today for a no-obligation chat.

Supermicro GB300 NVL72 Deployment Scenarios

Supermicro GB300 NVL72 is a high-capacity AI rack for frontier training, large-context inference and multi-rack model workloads. It fits organisations that have outgrown earlier Blackwell systems and need more memory, fabric headroom and operational stability in one production platform.

AI Factory Rack for Hyperscale Data Centres

Data centre teams deploy the GB300 NVL72 where frontier and agentic AI models are pushing past first-generation rack limits. It helps reduce extra rack sprawl for larger models, while giving operators more room for heavy east-west traffic and power-intensive builds.

Frontier Model Development Environments

Software development teams use this platform for large-context training and validation when model partitioning slows iteration. The extra capacity supports larger experiments across fewer cuts, giving engineers more headroom as training and inference demands expand across racks.

Private AI for Financial Services

In finance, the GB300 NVL72 suits tightly controlled environments running generative AI, fraud detection and quantitative workloads. Its larger memory and fabric headroom help firms keep sensitive models in-house while avoiding early limits on scale and cluster communication.

Research Compute for Healthcare and Life Sciences

Healthcare research teams deploy it for multimodal, molecular and imaging AI that outgrows smaller GPU systems. The rack-level capacity supports larger datasets and models with less fragmentation, which is important when discovery work must stay on schedule and under control.

Central AI Infrastructure for Manufacturing

Manufacturing organisations use the GB300 NVL72 as a central training platform for digital twins, robotics and multimodal model development. It gives engineering teams the capacity to simulate larger systems and iterate faster without spreading workloads across too many nodes.

Planning a Supermicro GB300 NVL72 Deployment?

Our team can help design and deploy Supermicro GB300 NVL72 for AI factory, finance, healthcare, software development and manufacturing environments, with the right sizing, integration and recovery approach for your operational constraints.

Spread the cost of your next IT upgrade or refresh!

Many of our vendor partners offer their own flexible finance programs, available for orders over a certain threshold. 

 

As part of our free consultation and advisory service, we can:

Alternatively, we also work independently with third-party organisations to offer the best possible flexible leasing solutions.

 

Our team is here to help your businesses avoid upfront costs and keep your next IT project on budget. Submit an enquiry today to explore your options.

Trade-in your old IT hardware to save money on your purchase!

Instead of letting unused hardware depreciate or go to waste, our simple IT Asset Trade-In Service helps businesses to regain capital or receive credit towards future purchases.

Our team will assesses the market value of your equipment, managing the entire process from secure collection through to resale or responsible recycling.

To get started, simply submit an enquiry and we’ll respond within 24 working hours.

As a certified partner to industry-leading vendors, we provide access to promotions that reduce upfront spend and accelerate upgrade strategies.

When you work with us, we can bundle and stack multiple offers, navigate application processes, and secure pricing that often isn’t accessible without an official vendor partner.

 

Visit our promotions hub to explore current offers and discuss your eligibility.

Tailored recommendations for your infrastructure

Below you’ll find alternative models, suitable software and services that pair with this solution – helping you to avoid compatibility issues, reduce support overhead and deploy with confidence.

Not sure where to start?

Not all deployments fit standard configurations. If you’re weighing up options or want a second opinion on your setup, our team is here to help with honest, straightforward advice backed by decades of vendor knowledge.

Why choose us?

Expert advice

Get the right solution for your environment.

Access to leading vendors

Official partner across major technology brands.

Competitive pricing

Get the best value for your infrastructure.

Ongoing support

We’re here throughout the lifecycle.

Need help with this product?

Not sure which configuration, licence or support option is right for your requirements? Tell us what you need and our team can help with selection, compatibility, pricing and availability.

Need to define the right IT solution?

Alternatively, If you’re unsure whether this product fully meets your project’s needs, we’re here to help.
A group discussing IT solutions