Four-GPU inference server for departmental AI, air-cooled and rack-ready.
A rack server holding four GPUs. It suits a comms room or colocation rack and serves models for a whole team or application.
Best for
An older data centre GPU that still performs well for many workloads and is one of the cheapest routes into 80 GB of GPU memory.
Memory
80 GB
Deployment
Rack server
£6,450
ex VAT
In stock
A practical all-rounder. It serves AI models well and also handles rendering and virtual desktops, which makes it easy to justify in mixed environments.
Memory
48 GB
Deployment
Rack server
£7,995
ex VAT
In stock
A small, efficient card that fits in ordinary servers without extra power cables. Ideal for adding modest AI capability to existing infrastructure.
Memory
24 GB
Deployment
Rack server
£2,295
ex VAT
In stock