AMD
Popular

AMD Instinct MI300X

192GB HBM3 — proven ROCm performance with the best inference economics

Reserved and on-demand, self-service access

£2.70/hr starting£1,970/mo from

Reserved and committed-use discounts up to 60%. All prices GBP, ex-VAT.

Compare AMD GPUs

MI300X is the proven CDNA 3 accelerator powering the largest ROCm deployments in production. Outstanding inference economics and broad framework support.

Memory
192GB HBM3
5.3 TB/s bandwidth
Architecture
CDNA 3
Family · AMD Instinct
Compute (FP16)
1.6 PFLOPS (8-GPU)
BF16: 1.6 PFLOPS (8-GPU)
Interconnect
800G RoCE / Infinity Fabric
TDP · 750W

Highlights

  • 192GB HBM3 — fits Llama-3 70B in a single GPU
  • Mature ROCm ecosystem, drop-in for most CUDA kernels
  • Best price/performance for inference today

Software stack

ROCm 6.2+
PyTorch 2.3+
Triton
vLLM-ROCm
RCCL

Best-fit scenarios

  • Mid-to-large LLM inference
  • Multimodal training (vision + language)
  • Cost-sensitive HPC workloads

Pricing by configuration

All available SKUs for this GPU across bare-metal, VM and container form factors. Reserved and committed-use discounts available.

On-demand starting at £2.70/h

ConfigurationGPUsVRAM totalCPUMemoryStorageNetwork£/hr£/mo
Bare Metal — 8× MI300X
mi300x-bm-8
81.5 TB192 vCPU2 TB DDR58× 3.84 TB NVMeRoCE£19.60£14,240
Virtual Machine — 1× MI300X
mi300x-vm-1
1192GB32 vCPU256 GB1.92 TB NVMe100G£2.99£2,190
Container — 1× MI300X
mi300x-ctr-1
1192GB16 vCPU128 GB500 GB100G£2.70£1,970

Prices shown are list prices in GBP (ex-VAT). Reserved capacity and committed-use discounts up to 60% available — contact sales for a custom quote.

Technova at a glance

Full-stack AI cloud

GPUs, networking, storage, managed Slurm & Kubernetes on one platform.

Manual UK deployment

Every resource deployed and configured by our UK engineering team.

UK & US data residency

UK workloads stay in Glasgow & London. US workloads in Texas. You choose the region.

Reliable

Historical uptime over 99.9% with sensible SLAs and fair compensation.

Dual-stack CUDA + ROCm

Professional full-stack expertise across both NVIDIA and AMD.

World-class support

Proactive support from ML engineers and infrastructure specialists.

Ready to deploy AMD Instinct MI300X?

Spin up a private cluster in days, or talk to our sales engineers about custom configurations.

Explore AI Cloud