GPU NODES

AMD Instinct MI250X

AMD Instinct™ MI250X Series accelerators are uniquely suited to power even the most demanding AI and HPC workloads, delivering exceptional compute performance, massive memory density, high-bandwidth memory, and support for specialised data formats.

Key Facts

220 CUs
GPU Compute Units
Allowing for large parallelisation of AI workloads.
128 GB
HBM2e Dedicated Memory
1.6x the memory capacity compared to competing accelerators.
3.2 TB/s
Max theoretical memory bandwidth
Beating the peak theoretical memory bandwidth of competing accelerators.
400 GB/s
Peak Aggregate Infinity Fabric
Delivers up to 4X advantage vs. competitive NVIDIA A100 GPUs.

Our Nodes

We built our GPU nodes for those who want the raw performance of bare metal GPUs. Say good bye to bloated infrastructure environments and hello to simplicity.

Each one of our nodes is created from 8 highly optimised and fully connected MI250X GPUs.
AMD Specifications
AMD Instinct MI300X technology

AMD Instinct Series

AMD Instinct accelerators are built on AMD CDNA™ architecture, which offers Matrix Core Technologies and support for a broad range of precision capabilities—from the highly efficient INT8 and FP8 to the most demanding FP64 for HPC.

AMD ROCm™ software includes a broad set of programming models, tools, compilers, libraries, and runtimes for AI models and HPC workloads targeting AMD Instinct accelerators.
Read More
Nscale's vertically integrated suite of services and compute

Get access to a fully integrated
suite of AI services 
and compute

Reduce costs, grow revenue, and run your AI workloads more efficiently on a fully integrated platform. Whether you're using Nscale's built-in AI/ML tools or your own, our platform is designed to simplify the journey from development to production.

Marketplace
Training
Inference
GPU nodes
Nscale's Datacentres
Powered by 100% renewable energy
LLM Library
Pre-configured Software
Pre-configured Infrastructure
Job Management
Job-scheduling
Container Orchestration
Optimised Libraries
Optimised Compilers and Tools
Optimised Runtime

Access thousands of GPUs tailored to your requirements.