Shop/AMD Instinct MI355X

AMD Instinct MI355X

288 GB AMD accelerator aimed at large-model inference and ROCm training.

Request quote

In plain English

AMD's flagship accelerator. Very large memory per GPU means fewer GPUs are needed to hold a big model.

Best for

Data Centre AI Accelerators

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

DatacentreHigh-Memory

Price on request

Allocation only

AI Clusters and Rack-Scale

A complete private AI environment in one rack: servers, network, storage and installation, commissioned by our engineers.

Memory

Configurable

Deployment

Datacentre

Multi-GPUProduction Inference

Price on request

Available to order