(02) 9388 1741
Request a Quote Shipping Information Contact Us Compare Products
Resources
Documentation & Support

Access product documentation, technical guides, downloads, and helpful resources to support your Supermicro server solutions.

Browse Resources
Federal Government State Government Local Government
For Government
For Government

A trusted partner delivering secure, compliant IT solutions for Australian federal, state, and local government agencies.

Contact Us
Servers & Storage
Rackmount Server Solutions
Supermicro GPU Servers
Twin Multi-Node Systems
Blade Server Solutions
Storage Servers Solutions
Building Blocks
Server Boards
Workstation Board
Embedded IoT Board
Desktop Gaming Board
SuperIO
Others
Rack Series
MGX 1.2 Rack Series
MGX 1.1 Rack Series
EIA 19" Rack Series
OCP ORv3 Rack Series
Others
Server Chassis & Cases
1U
2U
3U
Mini 1U
4U
MidTower
Others
Compact Mini Tower
5U Full Tower
Mini Tower
Edge, Embedded, & Telecom
Edge AI and IoT Systems
Networking
Networking Switches
Networking Adapters
Client
SuperWorkstations
Desktop Systems
Gold Series
Enterprise Compute
Enterprise AI
Enterprise Storage
Intelligent Edge
Client & Workstation
Data Center Building Blocks Solutions
In-Rack Solutions
Site Infrastructure Solutions
Management Software Suite
Rear Door Heat Exchange (RDHx)
Supplementary Heat Removal
Advanced Heat Removal
Maximum Heat Removal
Generative AI SuperCluster
Generative AI SuperCluster
System Management Software
System Management Software
Contact Us (02) 9388 1741
Show All Products
NVIDIA GB200 NVL72
Generative AI SuperCluster

NVIDIA GB200 NVL72

NVIDIA GB200 NVL72: 72 NVIDIA Blackwell GPUs, Pioneers in Liquid Cooling, Unmatched Manufacturing Scale, Comprehensive Service Offering.

Supermicro Products
Generative AI SuperCluster
NVIDIA GB200 NVL72
Scalable Unit: 72-GPU Scalable Unit  |  Gpus: 72x NVIDIA Blackwell B200 GPUs  |  Cpus: 36x NVIDIA 72-core Grace Arm Neoverse V2
#SRS-GB200-NVL72-M1
Our Price: Request a Quote
Get a Quote

Details that matter

Engineered for professionals who demand the best in performance, security, and design.

72 NVIDIA Blackwell GPUs

acting as one GPU with a massive pool of HBM3e memory to deliver the most efficient exascale computing in a rack

Pioneers in Liquid Cooling

total liquid-cooling solution with up to 40% reduction in electricity cost for data center

Unmatched Manufacturing Scale

with the largest liquid cooling rack-level manufacturing capacity, Supermicro ensures timely and high-quality deployment of the GB200 NVL72, supported by production facilities in San Jose, CA, Europe, and Asia

Comprehensive Service Offering

from proof of concept to full-scale deployment, Supermicro is one-stop shop, providing all necessary parts, networking solutions, and on-site installation services

Advanced Networking Ready

Supermicro is at the forefront of adopting NVIDIA BlueField®-3, Spectrum™-X, Quantum-2, and next generation 800 Gb/s networking platforms

Technical Specifications

Full specifications for the model

SKU SRS-GB200-NVL72-M1
Scalable Unit 72-GPU Scalable Unit
Gpus 72x NVIDIA Blackwell B200 GPUs
Cpus 36x NVIDIA 72-core Grace Arm Neoverse V2
Compute Trays 18x 1U Compute Trays
Nvlink Switch Trays 9x NVLink Switch, 4-ports per compute tray connecting 72 GPUs to provide 1.8TB/s GPU-to-GPU interconnect
Power Shelves 8x 1U 33kW (6x 5.5kW PSUs), total power 132kW
Operating Power 125kW to 135kW
Rack Dimensions Mm 2236mm x 600 mm x 1068mm
Liquid Cooling Options 1x in-rack Supermicro 4U 250kW capacity CDU with redundant PSU and dual hot-swap pumps
1.3MW capacity in-row CDU
Optional 180kW/240kW capacity liquid-to-air solutions for facilities without cooling tower and water supply
Compute Tray Overview 1U Liquid-cooled System with 2 NVIDIA GB200 Grace Blackwell Superchips
Compute Tray Cpu And Gpu 2 72-core NVIDIA Grace Arm Neoverse V2 CPUs
4 NVIDIA Blackwell Tensor Core GPUs
Compute Tray Gpu Memory Up to 372GB HBM3e per Superchip (744GB per tray)
Compute Tray Cpu Memory Up to 480GB LPDDR5X per Superchip (960GB per tray)
Compute Tray Networking 4 NVIDIA NVLink Switch ports (rear)
4 single-port NVIDIA ConnectX®-7 NICs (front)
Up to 2 NVIDIA BlueField®-3 DPUs (front)
Compute Tray Storage Up to 8 E1.S PCIe 5.0 drives
Compute Tray Power Supply Shared power through 4+4 rack power shelves

Documentation

Download product documentation and resources

Product Datasheet

NVIDIA GB200 NVL72 Datasheet

Custom Configurations

Looking for more configuration options or custom setups? Our team can help you find the right solution based on your requirements.

Contact Us

Bulk Purchase Support

Need multiple devices for your business or project? Contact us to discuss bulk pricing, availability, and delivery options.

Contact Us
Discover More

Similar Products

Explore other configurations and models that might suit your needs.

Liquid-Cooled 2 OU NVIDIA HGX™ B300 AI Cluster Recommended

Liquid-Cooled 2 OU NVIDIA HGX™ B300 AI Cluster

#SYS-222GS-NB3OT-ALC

Liquid-Cooled 2 OU NVIDIA HGX™ B300 AI Cluster: 2-OU Liquid-cooled system with front I/O NICs, DPUs, storage, and management.

  • Overview: 2-OU Liquid-cooled system with front I/O NICs, DPUs, storage, and management
  • Cpu: Dual Intel® Xeon® 6700 series processors with P-cores
  • Memory: 32 DIMMs, up to 8TB DDR5-5200 or up to 4TB DDR5-6400
View Details
SuperCluster SRS-48UAC-B300SX Recommended

SuperCluster SRS-48UAC-B300SX

#SuperCluster SRS-48UAC-B300SX

SuperCluster SRS-48UAC-B300SX: Full-Stack Reference Architecture, Up to 256x NVIDIA HGX™ B300 GPUs, NVIDIA Software Stack Compatibility, Plug-and-Play Integration.

  • Cluster Compute Nodes: 4, 8, or 32 nodes (32–256 GPUs) per scalable unit
  • Compute Racks: Up to 8x compute racks per scalable unit
  • Networking Racks: 1x networking rack per scalable unit
View Details
Liquid-Cooled NVIDIA HGX B200 AI Cluster Recommended

Liquid-Cooled NVIDIA HGX B200 AI Cluster

#SRS-48UDLC-4U8N-L1

Liquid-Cooled NVIDIA HGX B200 AI Cluster: Fully integrated liquid-cooled 32-node cluster with 256 NVIDIA B200v GPUs.

  • Scalable Unit: 2-Node Scalable Unit
  • Overview: Fully integrated liquid-cooled 32-node cluster with 256 NVIDIA B200v GPUs
  • Compute Fabric Leaf: 8x NVIDIA Quantum-2 400G InfiniBand Switch or 8x NVIDIA Spectrum-4 400GbE Ether…
View Details

Call a Specialist
Today!

Our team of experts is ready to help you find the perfect solution for your business needs. Get personalized advice and competitive quotes.

Monday - Friday: 9:00 AM - 6:00 PM AEST
Sydney, Australia
Request a Quote Contact Us

Speak to an Expert

We're here to help with any questions

Call us now
(02) 9388 1741