Compare instance

AWS Amazon EC2

p5.48xlarge

⚡ 8x GPU • 640.0 GB HBM3

Part of the P5 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:pGPU Deep Learning & HPCp = GPU Deep Learning & HPCHigh-end NVIDIA GPUs (Blackwell, Hopper, Ampere, Volta) built for frontier AI/LLM training, HPC simulations, and generative AI.55th Generation5 = 5th GenerationAWS 5th generation hardware platform with updated CPU/system architecture.48xlarge48 Extra Large48xlarge = 48 Extra Large192 vCPUs • 2,048 GB RAM • 30720 GB SSD • 3200 Gbps Network • 8x NVIDIA H100 (640.0 GB VRAM)
On-demand, Linux
$55.0400/ hr
~$40,179.20/mo · lowest in US East (Atlanta), us-east-1-atl-1
Savings Plan, Linux
$40.42138/ hr
From, with a 3-year Compute Savings Plan, No Upfront: −27% vs on-demand rate (us-east-1-atl-1)
Per unit
$0.2867/ vCPU-hr
$0.0269/GB-hr
Compute
192vCPUs
96 cores • x86_64
Memory
2,048GB
10.7 GB / vCPU
Network
3200 Gbps
Baseline: 3200 Gbps
Storage & EBS
10,000MB/s
Max: 260,000 IOPS

On Google Cloud

p5.48xlarge is an accelerated machine. Those are compared by the accelerator, not by vCPU and memory, so this page doesn't pick a match. Browse Google Cloud machines.

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads192 vCPUs
Physical Cores96
Clock Speed2.95 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score3,900,325
CoreMark / vCPU20,314.2 / core
FFmpeg Transcoding—
CoreMark per Dollar70,863 score / $
Cost per vCPU-hr$0.2867
Cost per GB-hr$0.0269

Containers & Kubernetes

EKS Max Pods100 pods
Max ENIs64
IPv4/v6 per ENI50
Total Addressable IPs3200 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance3200 Gbps
Baseline Bandwidth3200 Gbps
Burst / Peak Bandwidth3200 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationSSD (30720 GB)
Local NVMe Disk30,720 GB SSD
EBS Baseline Throughput10000 MB/s
EBS Max Throughput10000 MB/s
EBS Baseline IOPS260,000
EBS Max / Burst IOPS260,000
Dedicated EBS Throughput80 Gbps

GPU & Hardware Acceleration

GPU ModelNVIDIA H100
Accelerator Count8x GPU(s)
Total GPU Memory640.0 GB
Memory ArchitectureHBM3
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor384
Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$55.0400/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$92.4672/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$66.7704/ hr
Across all active regions
Regional Coverage
16regions
Available worldwide
Linux — Available in all 16 regions
RegionOn-Demand Price
ap-southeast-3
Asia Pacific (Jakarta)
$75.9552
ap-south-1
Asia Pacific (Mumbai)
$66.0480
ap-northeast-2
Asia Pacific (Seoul)
$75.9552
ap-southeast-2
Asia Pacific (Sydney)
$71.5520
ap-northeast-1
Asia Pacific (Tokyo)
$68.8000
us-gov-west-1
AWS GovCloud (US-West)
$66.0480
ca-central-1
Canada (Central)
$63.2960
eu-central-1
EU (Frankfurt)
$68.8000
eu-west-2
EU (London)
$71.5520
eu-north-1
EU (Stockholm)
$58.8928
sa-east-1
South America (Sao Paulo)
Highest
$92.4672
us-east-1-atl-1
US East (Atlanta)
Lowest
$55.0400
us-east-1
US East (N. Virginia)
Lowest
$55.0400
us-east-2
US East (Ohio)
Lowest
$55.0400
us-west-1
US West (N. California)
$68.8000
us-west-2
US West (Oregon)
Lowest
$55.0400