Most people arrive knowing the model, not the memory requirement. Start here and we will work backwards to the infrastructure.
~90 GB
Based on weights at the chosen precision plus working memory for context and concurrency. Real requirements vary with context length, batching and the serving framework. Treat this as a starting point for a conversation, not a specification.
A large-memory workstation card. It fits into a professional tower and lets you run or fine-tune substantial models on your own hardware.
Memory
96 GB
Deployment
Deskside workstation
£7,495
ex VAT
In stock
The server version of the RTX PRO 6000. It has no fan of its own and relies on the server's airflow, so it belongs in a certified rack server rather than a desktop.
Memory
96 GB
Deployment
Rack server
£8,250
ex VAT
Available to order
A small desk-side machine that can hold surprisingly large models because its memory is shared between the CPU and GPU. It is a development machine rather than a production server.
Memory
128 GB
Deployment
Datacentre
£2,995
ex VAT
In stock
A compact computer built to run AI where the work happens — on a robot, a vehicle or a production line — rather than in a datacentre.
Memory
128 GB
Deployment
Datacentre
£2,850
ex VAT
Available to order
A very capable data centre GPU in card form, so it can be fitted into common rack servers rather than requiring a specialist chassis.
Memory
141 GB
Deployment
Rack server
£24,950
ex VAT
Low stock
The mainstream high-end training GPU. Sold as part of an eight-GPU server rather than as a card you fit yourself.
Memory
180 GB
Deployment
Rack server
From £32,500
ex VAT
Available to order
Deployment classes shown on each card: Deskside workstation, Rack server, Datacentre.
Everything here is priced and confirmed by a person before anything is agreed.