From a 32 GB desk-side card to rack-scale accelerators. Filter by manufacturer, architecture, condition and how you want to buy.
12 products · prices excluding VAT
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
Price on request
Available to order
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
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
A used but professionally tested H100. The same silicon as new stock, at a lower price, with a warranty and a documented test report.
Memory
80 GB
Deployment
Rack server
£15,750
ex VAT
In stock
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
A mid-range professional GPU with enough memory for most day-to-day AI development work without the cost of a 96 GB card.
Memory
48 GB
Deployment
Deskside workstation
£4,295
ex VAT
In stock
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
A consumer graphics card that is very capable for local AI. Memory is the limit: it runs small and medium models well, but not the largest ones.
Memory
32 GB
Deployment
Desktop system
£1,849
ex VAT
In stock
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 proven AMD accelerator with 192 GB of memory, frequently chosen for serving large language models economically.
Memory
192 GB
Deployment
Rack server
Price on request
Available to order
NVIDIA Blackwell Ultra
Top of the current NVIDIA data centre range for large-scale AI training and inference.
NVIDIA Blackwell
Current-generation data centre accelerators for training and production inference.
NVIDIA Hopper
Proven previous-generation accelerators, widely available new and refurbished.
NVIDIA L40S, L4 and Inference GPUs
Efficient data centre GPUs for inference, graphics and mixed workloads.
NVIDIA RTX PRO Blackwell
Professional workstation GPUs with large memory for desk-side AI.
NVIDIA Consumer and Prosumer AI
Entry point for local AI experimentation and small-scale inference.
AMD Instinct MI350 Series
Current AMD data centre accelerators with very large memory capacity.
AMD Instinct MI300 Series
Established AMD accelerators available new and refurbished.