AWS Amazon EC2

g5g.8xlarge

⚡ 1x GPU • 16 GB

Part of the G5G Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inference55th GenerationgAWS Graviton8xlarge8 Extra Large

On-demand, Linux

$1.3720/ hr

~$1,001.56/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$0.7409/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −46% vs on-demand rate (us-east-1)

Per unit

$0.0429/ vCPU-hr

$0.0214/GB-hr

Compute

32vCPUs

32 cores • arm64

Memory

64GB

2.0 GB / vCPU

Network

Up to 12 Gbps

Baseline: 12 Gbps

Storage & EBS

1,187.5MB/s

Max: 40,000 IOPS

On Google Cloud

g5g.8xlarge 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

ProcessorAWS Graviton2 Processor

Architecturearm64 (ARM64 (Graviton))

vCPUs / Threads32 vCPUs

Physical Cores32

Clock Speed2.5 GHz

Intel AVX / AVX2No

Intel Turbo BoostNo

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score622,245

CoreMark / vCPU19,445.2 / core

FFmpeg Transcoding100 FPS

CoreMark per Dollar453,531 score / $

Cost per vCPU-hr$0.0429

Cost per GB-hr$0.0214

Containers & Kubernetes

EKS Max Pods234 pods

Max ENIs8

IPv4/v6 per ENI30

Total Addressable IPs240 total IPs

CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network PerformanceUp to 12 Gbps

Baseline Bandwidth12 Gbps

Burst / Peak Bandwidth12 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only

Local NVMe DiskNone (EBS only)

EBS Baseline Throughput1187.5 MB/s

EBS Max Throughput1187.5 MB/s

EBS Baseline IOPS40,000

EBS Max / Burst IOPS40,000

Dedicated EBS Throughput9500 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA T4g

Accelerator Count1x GPU(s)

Total GPU Memory16.0 GB

Memory Architecture—

Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)

Nitro EnclavesSupported (Isolated security enclaves)

Normalization Factor3.266666667

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$1.3720/ hr

US East (N. Virginia) (us-east-1)

Highest Price Region

$1.9198/ hr

Asia Pacific (Singapore) (ap-southeast-1)

Global Fleet Average

$1.6358/ hr

Across all active regions

Regional Coverage

7regions

Available worldwide

Linux — Available in all 7 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-northeast-2 Asia Pacific (Seoul)	$1.6876
ap-southeast-1 Asia Pacific (Singapore) Highest	$1.9198
ap-northeast-1 Asia Pacific (Tokyo)	$1.8519
eu-central-1 EU (Frankfurt)	$1.7163
eu-south-2 Europe (Spain)	$1.5311
us-east-1 US East (N. Virginia) Lowest	$1.3720
us-west-2 US West (Oregon) Lowest	$1.3720

Savings Plans: what to know

A Savings Plan commits you to a dollar amount per hour of spend for one or three years, not to an instance: usage up to that amount is billed at the plan's rates and the rest at on-demand, and unused commitment is still billed.
A Compute Savings Plan follows your usage across instance families, sizes, regions and operating systems; an EC2 Instance Savings Plan is locked to one family in one region in exchange for a lower rate (what that flexibility costs).
In US East (N. Virginia) (us-east-1), the 3-year Compute Savings Plan rate (No Upfront) for g5g.8xlarge on Linux is 54% of the on-demand rate, so the instance has to run at least 54% of the hours for the commitment to cost less than on-demand.
Rates are AWS's effective hourly rate for each payment option; All Upfront pays the whole term's commitment at purchase, which is why its hourly rate is lower; Partial Upfront (at least half up front) isn't shown on this page. The Savings Plans calculator has all three and sizes a commitment for this instance or a mix of them. How AWS applies a plan each hour: how Compute Savings Plans decide what they cover. Sizing one for elastic workloads: managing Compute Savings Plans.