Skip to content
Data PrivateStorage Solutions

8U Server with 8x NVIDIA HGX B300 (SYS-822GS-NB3RT-01-G2)

Starting at$848,075.67

In Stock

Confirmed at quotation

  • Key Features/Applications: Large scale AI inference serving, scientific research, conversational AI, AI and deep learning training, large language models and generative AI
  • CPU: Dual Intel Xeon 6768P Processors, 64 cores each
  • Chassis: 8U Rackmount
  • Drive: 1 x 960 GB M.2 NVMe
  • RAM: 16 x 128 GB DDR5-6400 RDIMM
  • GPU: NVIDIA HGX GPU baseboard, 8 x B300 NVL8
  • Network Ports: 8-Port 800GbE XDR800

Request a quotation for volume pricing

Request a Quotation
SKU: IV-SM-SYS-822GS-NB3RT-01-G2 Category:

Shipped Configuration

The base build as despatched. Every component group can be specified differently against your requirement, and the revised price is confirmed in a written quotation.

  • CPUDual Intel Xeon 6768P Processors, 64 cores each
  • Memory16 x 128 GB DDR5-6400 RDIMM
  • Storage1 x 960 GB M.2 NVMe
  • AOC8-Port 800GbE XDR800
  • GPUNVIDIA HGX GPU baseboard, 8 x B300 NVL8

Warranty and Onsite Service

Included

3 Years Parts and Labour

Cover is the manufacturer warranty applicable to this product and region. Onsite service and extended terms can be added at quotation stage.

Configuration Summary

  • CPUDual Intel Xeon 6768P Processors, 64 cores each
  • Memory16 x 128 GB DDR5-6400 RDIMM
  • Storage1 x 960 GB M.2 NVMe
  • AOC8-Port 800GbE XDR800
  • GPUNVIDIA HGX GPU baseboard, 8 x B300 NVL8
  • Warranty3 Years Parts and Labour
Request a Quotation

Need help specifying this system?

Rack power, cooling capacity and network topology all change what will actually work on your site. Tell us the environment and we will come back with a configuration that fits it.

Talk to a specialist
Key Features/Applications

Large scale AI inference serving, scientific research, conversational AI, AI and deep learning training, large language models and generative AI

CPU

Dual Intel Xeon 6768P Processors, 64 cores each

Chassis

8U Rackmount

Drive

1 x 960 GB M.2 NVMe

RAM

16 x 128 GB DDR5-6400 RDIMM

GPU

NVIDIA HGX GPU baseboard, 8 x B300 NVL8

Network Ports

8-Port 800GbE XDR800

Model

SYS-822GS-NB3RT-01-G2

Series

Gold Series

Form Factor

8U Rackmount

GPU Architecture

NVIDIA Blackwell Ultra

GPU Count

8

Processor Family

Intel Xeon 6768P

Processor Count

2

Cores per Processor

64

Total System Memory

2,048 GB DDR5-6400 RDIMM

Memory Modules

16 x 128 GB

Boot Storage

1 x 960 GB M.2 NVMe

Warranty

3 Years Parts and Labour

Lead Time

Confirmed at quotation

Overview

The SYS-822GS-NB3RT-01-G2 is a pre-validated Gold Series build for large scale AI inference serving, scientific research, conversational AI, deep learning training and generative AI workloads. It carries an NVIDIA HGX GPU baseboard with eight B300 NVL8 accelerators, dual Intel Xeon 6768P processors at 64 cores each, and sixteen 128 GB DDR5-6400 registered modules.

East-west traffic is handled by eight 800GbE XDR800 ports, so the platform is designed to sit inside a scaled cluster rather than as an isolated node.

Before you order

Gold Series platforms are held as pre-built configurations, so the base build ships faster than a made to order system. The figure shown is the starting price for that base build. Rack power, containment and cooling capacity should be confirmed against your site before order.