p5.4xlarge
Amazon EC2 instance p5.4xlarge with 16 vCPUs, 256 GiB RAM and 1 x NVIDIA H100 80 GiB. Available in 10 regions starting from $5022.40 per month.
| p5.4xlarge |
| GPU instance |
| GPU intensive tasks like machine/deep learning, high-performance computing p – Performance / GPU (Graphics Processing Unit) accelerated 5 – Generation 4xlarge – Size |
| 16 |
| 256 GiB |
| x86_64 |
| AMD EPYC 7R13 Processor |
| 3.6 GHz |
| 2 |
| yes |
| H100 |
| NVIDIA |
| 1 |
| 80 GiB |
| 80 GiB |
| no |
| 803 GiB |
| no |
| no |
| no |
| no |
| 1 x 3840 GB SSD |
| default |
| supported |
| required |
| 10240 MBps |
| 10000 Mbps |
| 1250 Mbps |
| 32500 IOPS |
| 32500 IOPS |
| 10000 Mbps |
| 1250 Mbps |
| 100 Gigabit |
| yes |
| 4 |
| 1 |
| 30 |
| 30 |
| yes |
| required |
| yes |
| 1 |
| yes |
| yes |
Regional Availability
US
GovCloud (US-East) / us-gov-east-1
GovCloud (US-West) / us-gov-west-1
US East (Ohio) / us-east-2
US East (Virginia) / us-east-1
US West (N. California) / us-west-1
US West (Oregon) / us-west-2
GovCloud (US-East) / us-gov-east-1
GovCloud (US-West) / us-gov-west-1
US East (Ohio) / us-east-2
US East (Virginia) / us-east-1
US West (N. California) / us-west-1
US West (Oregon) / us-west-2
Central America
Mexico (Central) / mx-central-1
Mexico (Central) / mx-central-1
Canada
Canada (Central) / ca-central-1
Canada West (Calgary) / ca-west-1
Canada (Central) / ca-central-1
Canada West (Calgary) / ca-west-1
Europe
Europe (Ireland) / eu-west-1
Europe (London) / eu-west-2
Europe (Frankfurt) / eu-central-1
Europe (Milan) / eu-south-1
Europe (Paris) / eu-west-3
Europe (Spain) / eu-south-2
Europe (Stockholm) / eu-north-1
Europe (Zurich) / eu-central-2
Europe (Ireland) / eu-west-1
Europe (London) / eu-west-2
Europe (Frankfurt) / eu-central-1
Europe (Milan) / eu-south-1
Europe (Paris) / eu-west-3
Europe (Spain) / eu-south-2
Europe (Stockholm) / eu-north-1
Europe (Zurich) / eu-central-2
Africa
Africa (Cape Town) / af-south-1
Africa (Cape Town) / af-south-1
South America
South America (São Paulo) / sa-east-1
South America (São Paulo) / sa-east-1
Asia Pacific
Asia Pacific (Hong Kong) / ap-east-1
Asia Pacific (Hyderabad) / ap-south-2
Asia Pacific (Jakarta) / ap-southeast-3
Asia Pacific (Malaysia) / ap-southeast-5
Asia Pacific (Melbourne) / ap-southeast-4
Asia Pacific (Mumbai) / ap-south-1
Asia Pacific (New Zealand) / ap-southeast-6
Asia Pacific (Osaka) / ap-northeast-3
Asia Pacific (Seoul) / ap-northeast-2
Asia Pacific (Singapore) / ap-southeast-1
Asia Pacific (Sydney) / ap-southeast-2
Asia Pacific (Taipei) / ap-east-2
Asia Pacific (Thailand) / ap-southeast-7
Asia Pacific (Tokyo) / ap-northeast-1
Asia Pacific (Hong Kong) / ap-east-1
Asia Pacific (Hyderabad) / ap-south-2
Asia Pacific (Jakarta) / ap-southeast-3
Asia Pacific (Malaysia) / ap-southeast-5
Asia Pacific (Melbourne) / ap-southeast-4
Asia Pacific (Mumbai) / ap-south-1
Asia Pacific (New Zealand) / ap-southeast-6
Asia Pacific (Osaka) / ap-northeast-3
Asia Pacific (Seoul) / ap-northeast-2
Asia Pacific (Singapore) / ap-southeast-1
Asia Pacific (Sydney) / ap-southeast-2
Asia Pacific (Taipei) / ap-east-2
Asia Pacific (Thailand) / ap-southeast-7
Asia Pacific (Tokyo) / ap-northeast-1
Middle East
Israel (Tel Aviv) / il-central-1
Middle East (Bahrain) / me-south-1
Middle East (UAE) / me-central-1
Israel (Tel Aviv) / il-central-1
Middle East (Bahrain) / me-south-1
Middle East (UAE) / me-central-1
Regional Prices
Geography | Region Name | Region | Savings Options | Instance Price |
|---|---|---|---|---|
| Hidden | Hidden | hidden-2 | compare | 6.8800 |
| Hidden | Hidden | hidden-3 | compare | 8.2560 |
| Hidden | Hidden | hidden-4 | compare | 8.6000 |
| Hidden | Hidden | hidden-5 | compare | 8.9440 |
| Hidden | Hidden | hidden-6 | compare | 8.9440 |
| Hidden | Hidden | hidden-7 | compare | 11.5584 |
| Asia Pacific | Asia Pacific (Mumbai) | ap-south-1 | compare | n/a |
| Asia Pacific | Asia Pacific (Jakarta) | ap-southeast-3 | compare | n/a |
| Hidden | Hidden | hidden-1 | compare | n/a |
| US | US East (Virginia) | us-east-1 | compare | n/a |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in p5.4xlarge's 80 GB of GPU memory. VRAM is estimated from the parameter count at the selected quantization, so treat it as guidance rather than a guarantee.
Chat Models
FP16 (full precision)
Model | Creator | Intelligence | Total params | Active params | ~VRAM | |
|---|---|---|---|---|---|---|
| Qwen3.6 27B | 45.8#51 | 27B | — | 65 GB | ||
| Qwen3.5 27B | 42.1#71 | 27B | — | 65 GB | ||
| Gemma 4 31B | 39.2#92 | 31B | — | 74 GB | ||
Similar Alternative Instances
Find Similar Instances In:
Instance Type | Region | vCPUs | Memory (GiB) | GPU Name | Instance Price | Price Diff % |
|---|---|---|---|---|---|---|
| g6e.2xlarge | US East (Virginia) (us-east-1) | 8 | 64 | L40S | 2.2421 | null% |
| g6e.4xlarge | US East (Virginia) (us-east-1) | 16 | 128 | L40S | 3.0042 | null% |
| g6e.8xlarge | US East (Virginia) (us-east-1) | 32 | 256 | L40S | 4.5286 | null% |
| g7e.2xlarge | US East (Virginia) (us-east-1) | 8 | 64 | RTX PRO Server 6000 | 3.3631 | null% |
| g7e.4xlarge | US East (Virginia) (us-east-1) | 16 | 128 | RTX PRO Server 6000 | 3.9982 | null% |