Top of the current NVIDIA data centre range for large-scale AI training and inference.
The newest and largest NVIDIA accelerators. These are bought by organisations training or serving very large AI models, normally installed in racks rather than a single machine.
Who it is for
Typical workloads
Previous: nvidia-blackwell
Next: —
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
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.
Memory
2304 GB
Deployment
Datacentre
Price on request
Allocation only