AMD
Large-model inference
192 GB per GPU for big models.
AMD Instinct MI300X servers.
Large-memory AI servers on the AMD Instinct MI300X. Built to your configuration with fast local storage and a fixed monthly price.
- 192 GB HBM3
- per GPU
- Up to 8
- GPUs per server
- NVMe
- local storage
- Quote
- priced to config
// Best for
What teams run on AMD Instinct MI300X.
AMD
ROCm workloads
PyTorch and JAX on ROCm.
AMD
HPC
Double-precision compute.
// Every GPU server includes
Built for sustained load.
- Access
- Full root
- Storage
- NVMe
- Network
- 10 to 100 Gbit/s
- Support
- Engineers 24/7
- Cooling
- Sized for full load
- Power
- Redundant feeds
- Setup fee
- $0
- Billing
- Fixed monthly
// Questions
GPU server FAQ.
- Is stock available now?
- We confirm stock and lead time in your quote.
- Can I rent one GPU or a full node?
- Both. Tell us the model and count and we price the node.
- What is the best fit?
- Inference for large models where memory per GPU decides the cost.