p5.4xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | p5.4xlarge |
Description | GPU accelerated Gen5 4xlarge |
Family | p5 |
Hw Virt | - |
Status | active |
Observed At | 2026-07-27T11:33:31.043262 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Northern Virgina (US) / us-east-1 | 2.85556 USD/h | 6.88 USD/h |
Ohio (US) / us-east-2 | 2.6295 USD/h | 6.88 USD/h |
Oregon (US) / us-west-2 | 2.6295 USD/h | 6.88 USD/h |
Mumbai (IN) / ap-south-1 | 8.256 USD/h | 8.256 USD/h |
Tokyo (JP) / ap-northeast-1 | 8.6 USD/h | 8.6 USD/h |
Sydney (AU) / ap-southeast-2 | - | 8.944 USD/h |
London (GB) / eu-west-2 | 8.944 USD/h | 8.944 USD/h |
Jakarta (ID) / ap-southeast-3 | 9.1419 USD/h | 9.4944 USD/h |
Sao Paulo (BR) / sa-east-1 | 9.499 USD/h | 11.5584 USD/h |
Processor
vCPUs | 16 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 8 |
CPU Speed | 3.6 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | AMD |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 256 GiB |
| GPU | |
|---|---|
GPU Count | 1 |
GPU Memory Min | 80 GiB |
GPU Memory Total | 80 GiB |
GPU Manufacturer | NVIDIA |
GPU Family | Hopper |
GPU Model | H100 |
GPUs |
|
| STORAGE | |
|---|---|
Storage Size | 3800 GB |
Storage Type | nvme ssd |
Storages |
|
| NETWORK | |
|---|---|
Network Speed Baseline | 100 Gbps |
Network Speed Max | 100 Gbps |
Network Storage Speed Baseline | 10 Gbps |
Network Storage Speed Max | 10 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
A high-density GPU instance featuring an NVIDIA Hopper H100 accelerator, massive system memory, and fast local NVMe SSD storage.
Amazon Web Services p5.4xlarge is a GPU-accelerated instance built on the Nitro hypervisor, featuring an x86_64 AMD processor with 16 vCPUs, 8 physical cores, and a 3.6 GHz clock speed. The hardware configuration includes 256.0 GB of system memory, a 3800 GB NVMe SSD for high-speed local storage, and a single NVIDIA Hopper H100 GPU with 80 GB of dedicated VRAM. Designed for demanding computational tasks, it delivers a baseline network bandwidth of 100 Gbps. This resource-dense profile offers high qualitative cost efficiency for single-GPU workloads by combining massive memory capacity with enterprise-grade acceleration. The p5.4xlarge is optimized for workloads such as deep learning model training, large language model inference, high-performance computing, and intensive data science operations.
Economics
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| p5.48xlarge | 192 | 2048 GiB | 8 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|