AWS Amazon EC2

g5.16xlarge

⚡ 1x GPU • 24 GB

Part of the G5 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inference55th Generation16xlarge16 Extra Large

On-demand, Linux

$4.0960/ hr

~$2,990.08/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$2.21184/ hr

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

Per unit

$0.0640/ vCPU-hr

$0.0160/GB-hr

Compute

64vCPUs

32 cores • x86_64

Memory

256GB

4.0 GB / vCPU

Network

25 Gbps

Baseline: 25 Gbps

Storage & EBS

2,000MB/s

Max: 65,000 IOPS

Alternatives to g5.16xlarge

Option	Price vs g5.16xlarge	Why look at it
g4dn.16xlarge Compare →	+6%+$0.256/hr Linux on-demand, us-east-1	Intel (x86_64), previous generation, same vCPU and RAM
g6.16xlarge Compare →	-17%-$0.699/hr Linux on-demand, us-east-1	Newer generation, same vCPU and RAM

On Google Cloud

g5.16xlarge 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 7R32

Architecturex86_64 (x86_64)

vCPUs / Threads64 vCPUs

Physical Cores32

Clock Speed2.8 GHz

Intel AVX / AVX2No

Intel Turbo BoostNo

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,246,915

CoreMark / vCPU19,483 / core

FFmpeg Transcoding113 FPS

CoreMark per Dollar304,423 score / $

Cost per vCPU-hr$0.0640

Cost per GB-hr$0.0160

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 Performance25 Gbps

Baseline Bandwidth25 Gbps

Burst / Peak Bandwidth25 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (1900 GB)

Local NVMe Disk1,900 GB NVMe SSD

EBS Baseline Throughput2000 MB/s

EBS Max Throughput2000 MB/s

EBS Baseline IOPS65,000

EBS Max / Burst IOPS65,000

Dedicated EBS Throughput16000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA A10G

Accelerator Count1x GPU(s)

Total GPU Memory24.0 GB

Memory Architecture—

Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)

Nitro EnclavesSupported (Isolated security enclaves)

Normalization Factor4.071570577

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$4.0960/ hr

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

Highest Price Region

$6.9624/ hr

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

Global Fleet Average

$5.0335/ hr

Across all active regions

Regional Coverage

19regions

Available worldwide

Linux — Available in all 19 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-east-1 Asia Pacific (Hong Kong)	$6.3060
ap-southeast-3 Asia Pacific (Jakarta)	$5.7328
ap-south-1 Asia Pacific (Mumbai)	$4.9185
ap-northeast-2 Asia Pacific (Seoul)	$5.0365
ap-southeast-2 Asia Pacific (Sydney)	$5.3256
ap-northeast-1 Asia Pacific (Tokyo)	$5.9404
ca-central-1 Canada (Central)	$4.5479
eu-central-1 EU (Frankfurt)	$5.1220
eu-west-1 EU (Ireland)	$4.5724
eu-west-2 EU (London)	$5.1994
eu-west-3 EU (Paris)	$5.1994
eu-north-1 EU (Stockholm)	$4.3444
eu-south-2 Europe (Spain)	$4.3159
il-central-1 Israel (Tel Aviv)	$4.8010
me-central-1 Middle East (UAE)	$5.0243
sa-east-1 South America (Sao Paulo) Highest	$6.9624
us-east-1 US East (N. Virginia) Lowest	$4.0960
us-east-2 US East (Ohio) Lowest	$4.0960
us-west-2 US West (Oregon) Lowest	$4.0960

Windows — Available in all 19 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-east-1 Asia Pacific (Hong Kong)	$9.2500
ap-southeast-3 Asia Pacific (Jakarta)	$8.6768
ap-south-1 Asia Pacific (Mumbai)	$7.8625
ap-northeast-2 Asia Pacific (Seoul)	$7.9805
ap-southeast-2 Asia Pacific (Sydney)	$8.2696
ap-northeast-1 Asia Pacific (Tokyo)	$8.8844
ca-central-1 Canada (Central)	$7.4919
eu-central-1 EU (Frankfurt)	$8.0660
eu-west-1 EU (Ireland)	$7.5164
eu-west-2 EU (London)	$8.1434
eu-west-3 EU (Paris)	$8.1434
eu-north-1 EU (Stockholm)	$7.2884
eu-south-2 Europe (Spain)	$7.2599
il-central-1 Israel (Tel Aviv)	$7.7450
me-central-1 Middle East (UAE)	$7.9683
sa-east-1 South America (Sao Paulo) Highest	$9.9064
us-east-1 US East (N. Virginia) Lowest	$7.0400
us-east-2 US East (Ohio) Lowest	$7.0400
us-west-2 US West (Oregon) Lowest	$7.0400

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 g5.16xlarge 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.
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.