Servers & Storage Building Blocks Rack Series Server Chassis & Cases
1U
2U
3U
4U
Edge, Embedded, & Telecom Networking Client Gold Series Data Center Building Blocks Solutions Rear Door Heat Exchange (RDHx) Generative AI SuperCluster System Management Software
Contact Us (02) 9388 1741
NVIDIA GB300 NVL72
Generative AI SuperCluster

NVIDIA GB300 NVL72

NVIDIA GB300 NVL72: Rack-Scale Solution, NVIDIA Blackwell Ultra Platform, Direct Liquid-Cooling Solution Stack, Comprehensive Service, Up to 800Gb/s Networking.

Supermicro Products
Generative AI SuperCluster
NVIDIA GB300 NVL72
Gpus: 72x NVIDIA B300 Tensor Core GPUs  |  Cpus: 36x NVIDIA 72-core Grace ARM Neoverse V2 CPUs  |  Compute Trays: 18x 1U ARS-121GL-NB3-LC
#SRS-GB300-NVL72-M1
Our Price: Request a Quote

Details that matter

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

Rack-Scale Solution

Rack-scale solution with NVIDIA GB300 Grace™ Blackwell Superchip providing 72 NVIDIA B300 GPUs and 36 Grace CPUs per rack

NVIDIA Blackwell Ultra Platform

NVIDIA Blackwell Ultra Platform with 288GB HBM3e per GPU*

Direct Liquid-Cooling Solution Stack

Supermicro Direct Liquid-Cooling total solution stack for fast deployment of liquid cooled data centers

Comprehensive Service

Comprehensive Service from consultation to full-scale deployment, providing all necessary parts, networking solutions, and onsite installation services

Up to 800Gb/s Networking

Up to 800Gb/s NVIDIA Quantum-X800 InfiniBand or Spectrum-X Ethernet with integrated NVIDIA ConnectX®-8 SuperNICs

Technical Specifications

Full specifications for the model

SKU SRS-GB300-NVL72-M1 / SRS-GB300-NVL72-M0
Gpus 72x NVIDIA B300 Tensor Core GPUs
Cpus 36x NVIDIA 72-core Grace ARM Neoverse V2 CPUs
Compute Trays 18x 1U ARS-121GL-NB3-LC
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) with built-in capacitor, total 132kW
Operating Power 132kW to 140kW
Rack Dimensions Mm 2236mm x 600 mm x 1068mm
Liquid Cooling Options In-Rack CDU: Up to 250kW capacity with N+1 redundant pumps
In-Row CDU: Up to 1.8MW capacity with N+1 redundant pumps (supports up to 8 racks)
L2A Sidecar CDU: Up to 200kW capacity CDU with N+1 redundant pumps (no facility water required)
Compute Tray Overview 1U liquid-cooled with 2 NVIDIA GB300 Grace Blackwell Superchips
Compute Tray Cpu And Gpu 2 72-core NVIDIA Grace ARM Neoverse V2 CPUs
4 NVIDIA B300 Tensor Core GPUs
Compute Tray Gpu Memory 1.15TB HBM3e per Compute Tray
Compute Tray Cpu Memory 960GB LPDDR5X per Compute Tray
Compute Tray Networking 4 NVIDIA NVLink Switch ports
4 integrated NVIDIA ConnectX®-8 SuperNICs, up to 800Gb/s
Up to 2 NVIDIA BlueField®-3 DPUs
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


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
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
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…

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

Speak to an Expert

We're here to help with any questions

Call us now
(02) 9388 1741