AWS Amazon EC2

g4dn.8xlarge

⚡ 1x GPU • 16 GB

Part of the G4DN Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inference44th GenerationdDirect-Attached NVMe SSDnEnhanced Networking8xlarge8 Extra Large

On-demand, Linux

$2.1760/ hr

~$1,588.48/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$1.1280/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −48% vs on-demand rate (us-east-1)

Per unit

$0.0680/ vCPU-hr

$0.0170/GB-hr

Compute

32vCPUs

16 cores • x86_64

Memory

128GB

4.0 GB / vCPU

Network

50 Gbps

Baseline: 50 Gbps

Storage & EBS

1,187.5MB/s

Max: 40,000 IOPS

Alternatives to g4dn.8xlarge

Option	Price vs g4dn.8xlarge	Why look at it
g5.8xlarge Compare →	+12%+$0.272/hr Linux on-demand, us-east-1	AMD (x86_64), newer generation, same vCPU and RAM
g6.8xlarge Compare →	-7%-$0.162/hr Linux on-demand, us-east-1	AMD (x86_64), newer generation, same vCPU and RAM
inf2.8xlarge Compare →	-10%-$0.208/hr Linux on-demand, us-east-1	AMD (x86_64), older generation, same vCPU and RAM

On Google Cloud

g4dn.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

ProcessorIntel Xeon Family

Architecturex86_64 (x86_64)

vCPUs / Threads32 vCPUs

Physical Cores16

Clock Speed2.5 GHz

Intel AVX / AVX2AVX & AVX2 Supported

Intel Turbo BoostYes

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score458,343

CoreMark / vCPU14,323.2 / core

FFmpeg Transcoding105 FPS

CoreMark per Dollar210,636 score / $

Cost per vCPU-hr$0.0680

Cost per GB-hr$0.0170

Containers & Kubernetes

EKS Max Pods58 pods

Max ENIs4

IPv4/v6 per ENI15

Total Addressable IPs60 total IPs

CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance50 Gbps

Baseline Bandwidth50 Gbps

Burst / Peak Bandwidth50 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (900 GB)

Local NVMe Disk900 GB NVMe SSD

EBS Baseline Throughput1187.5 MB/s

EBS Max Throughput1187.5 MB/s

EBS Baseline IOPS40,000

EBS Max / Burst IOPS40,000

Dedicated EBS Throughput7000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA T4

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 Factor4.136882129

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$2.1760/ hr

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

Highest Price Region

$3.6980/ hr

South America (Sao Paulo) (sa-east-1)

Global Fleet Average

$2.6738/ hr

Across all active regions

Regional Coverage

24regions

Available worldwide

Linux — Available in all 24 regions
Region	On-Demand Price	% vs On-Demand Rate
af-south-1 Africa (Cape Town)	$2.8870
ap-east-1 Asia Pacific (Hong Kong)	$3.3510
ap-south-1 Asia Pacific (Mumbai)	$2.3950
ap-northeast-3 Asia Pacific (Osaka)	$2.9380
ap-northeast-2 Asia Pacific (Seoul)	$2.6770
ap-southeast-1 Asia Pacific (Singapore)	$3.0450
ap-southeast-2 Asia Pacific (Sydney)	$2.8300
ap-northeast-1 Asia Pacific (Tokyo)	$2.9380
us-gov-east-1 AWS GovCloud (US-East)	$2.7430
us-gov-west-1 AWS GovCloud (US-West)	$2.7430
ca-central-1 Canada (Central)	$2.4160
eu-central-1 EU (Frankfurt)	$2.7200
eu-west-1 EU (Ireland)	$2.4260
eu-west-2 EU (London)	$2.5460
eu-south-1 EU (Milan)	$2.5470
eu-west-3 EU (Paris)	$2.5440
eu-north-1 EU (Stockholm)	$2.3080
me-south-1 Middle East (Bahrain)	$2.6690
sa-east-1 South America (Sao Paulo) Highest	$3.6980
us-east-1 US East (N. Virginia) Lowest	$2.1760
us-east-2 US East (Ohio) Lowest	$2.1760
us-west-2-lax-1 US West (Los Angeles)	$2.6110
us-west-1 US West (N. California)	$2.6110
us-west-2 US West (Oregon) Lowest	$2.1760

Windows — Available in all 24 regions
Region	On-Demand Price	% vs On-Demand Rate
af-south-1 Africa (Cape Town)	$4.3590
ap-east-1 Asia Pacific (Hong Kong)	$4.8230
ap-south-1 Asia Pacific (Mumbai)	$3.8670
ap-northeast-3 Asia Pacific (Osaka)	$4.4100
ap-northeast-2 Asia Pacific (Seoul)	$4.1490
ap-southeast-1 Asia Pacific (Singapore)	$4.5170
ap-southeast-2 Asia Pacific (Sydney)	$4.3020
ap-northeast-1 Asia Pacific (Tokyo)	$4.4100
us-gov-east-1 AWS GovCloud (US-East)	$4.2150
us-gov-west-1 AWS GovCloud (US-West)	$4.2150
ca-central-1 Canada (Central)	$3.8880
eu-central-1 EU (Frankfurt)	$4.1920
eu-west-1 EU (Ireland)	$3.8980
eu-west-2 EU (London)	$4.0180
eu-south-1 EU (Milan)	$4.0190
eu-west-3 EU (Paris)	$4.0160
eu-north-1 EU (Stockholm)	$3.7800
me-south-1 Middle East (Bahrain)	$4.1410
sa-east-1 South America (Sao Paulo) Highest	$5.1700
us-east-1 US East (N. Virginia) Lowest	$3.6480
us-east-2 US East (Ohio) Lowest	$3.6480
us-west-2-lax-1 US West (Los Angeles)	$4.0830
us-west-1 US West (N. California)	$4.0830
us-west-2 US West (Oregon) Lowest	$3.6480

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 g4dn.8xlarge on Linux is 52% of the on-demand rate, so the instance has to run at least 52% of the hours for the commitment to cost less than on-demand.
On Windows a plan discounts only the compute part of the rate: the Windows license part costs the same as on demand, so the percentage off is smaller than on Linux.
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.