AMD
Popular

AMD Instinct MI350X

288GB HBM3e flagship with native FP4/FP6 — the TCO leader for frontier inference

Reserved and on-demand, self-service access

£7.40/hr starting£5,400/mo from

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

Compare AMD GPUs

MI350X is AMD's flagship accelerator built on the CDNA 4 architecture, delivering unprecedented memory capacity and the new FP4/FP6 datapaths required by frontier model serving.

Memory
288GB HBM3e
8 TB/s bandwidth
Architecture
CDNA 4
Family · AMD Instinct
Compute (FP16)
2.5 PFLOPS (8-GPU)
BF16: 2.5 PFLOPS (8-GPU) · FP8: 5 PFLOPS (8-GPU)
Interconnect
800G Ultra Ethernet / RoCE v2
TDP · 1000W

Highlights

  • Industry-leading 288GB HBM3e per card
  • Native FP4/FP6 support for next-gen inference
  • Up to 40% lower TCO vs H200 on LLM inference

Software stack

ROCm 6.3
PyTorch 2.5
JAX
Triton
vLLM-ROCm

Best-fit scenarios

  • Frontier LLM training (100B+ parameters)
  • Long-context inference (1M+ tokens)
  • Mixture-of-Experts hosting

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 £7.40/h

ConfigurationGPUsVRAM totalCPUMemoryStorageNetwork£/hr£/mo
Bare Metal — 8× MI350X
Popular
mi350x-bm-8
82.3 TB192 vCPU (dual EPYC 9554)2 TB DDR58× 3.84 TB NVMeRoCE, full bisection£54.40£39,600
Virtual Machine — 1× MI350X
mi350x-vm-1
1288GB (PCIe passthrough)32 vCPU256 GB DDR51× 1.92 TB NVMe100G£8.00£5,850
Container — 1× MI350X
mi350x-ctr-1
1288GB16 vCPU128 GB500 GB ephemeral100G£7.40£5,400

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 MI350X?

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

Explore AI Cloud