Eight Blackwell Ultra SXM accelerators on a single HGX baseboard for OEM server integration.
The GPU engine used inside eight-way AI servers. It is fitted into a server chassis by the manufacturer, not installed like a plug-in card.
Best for
An entire rack delivered as one computer. It is bought for frontier model training and very large inference platforms, and requires liquid cooling and high-capacity power.
Memory
20736 GB
Deployment
Datacentre
Price on request
Allocation only
AMD's flagship accelerator. Very large memory per GPU means fewer GPUs are needed to hold a big model.
Memory
288 GB
Deployment
Datacentre
Price on request
Available to order
A complete private AI environment in one rack: servers, network, storage and installation, commissioned by our engineers.
Memory
Configurable
Deployment
Datacentre
Price on request
Available to order