AWS Amazon EC2

g6.2xlarge

⚡ 1x GPU • 24 GB

Part of the G6 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inference66th Generation2xlarge2 Extra Large

On-demand, Linux

$0.9776/ hr

~$713.65/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$0.5609/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −43% vs on-demand rate (us-east-1)

Per unit

$0.1222/ vCPU-hr

$0.0306/GB-hr

Compute

8vCPUs

4 cores • x86_64

Memory

32GB

4.0 GB / vCPU

Network

Up to 10 Gbps

Baseline: 5 Gbps

Storage & EBS

625MB/s

Max: 20,000 IOPS

Alternatives to g6.2xlarge

Option	Price vs g6.2xlarge	Why look at it
g5.2xlarge Compare →	+24%+$0.234/hr Linux on-demand, us-east-1	Previous generation, same vCPU and RAM
g4dn.2xlarge Compare →	-23%-$0.226/hr Linux on-demand, us-east-1	Intel (x86_64), older generation, same vCPU and RAM

On Google Cloud

g6.2xlarge 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 / Threads8 vCPUs

Physical Cores4

Clock Speed2.6 GHz

Intel AVX / AVX2No

Intel Turbo BoostNo

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score167,347

CoreMark / vCPU20,918.3 / core

FFmpeg Transcoding133 FPS

CoreMark per Dollar171,181 score / $

Cost per vCPU-hr$0.1222

Cost per GB-hr$0.0306

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 PerformanceUp to 10 Gbps

Baseline Bandwidth5 Gbps

Burst / Peak Bandwidth10 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (450 GB)

Local NVMe Disk450 GB NVMe SSD

EBS Baseline Throughput250 MB/s

EBS Max Throughput625 MB/s

EBS Baseline IOPS8,000

EBS Max / Burst IOPS20,000

Dedicated EBS ThroughputUp to 5000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L4

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 Factor1.21471173

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$0.9776/ hr

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

Highest Price Region

$1.6617/ hr

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

Global Fleet Average

$1.1952/ hr

Across all active regions

Regional Coverage

20regions

Available worldwide

Linux — Available in all 20 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-south-2 Asia Pacific (Hyderabad)	$1.1739
ap-southeast-5 Asia Pacific (Malaysia)	$1.2315
ap-south-1 Asia Pacific (Mumbai)	$1.1739
ap-northeast-2 Asia Pacific (Seoul)	$1.2021
ap-southeast-2 Asia Pacific (Sydney)	$1.2711
ap-northeast-1 Asia Pacific (Tokyo)	$1.4178
us-gov-east-1 AWS GovCloud (US-East)	$1.2322
us-gov-west-1 AWS GovCloud (US-West)	$1.2322
ca-central-1 Canada (Central)	$1.0855
eu-central-1 EU (Frankfurt)	$1.2225
eu-west-2 EU (London)	$1.2409
eu-west-3 EU (Paris)	$1.2409
eu-north-1 EU (Stockholm)	$1.0369
eu-south-2 Europe (Spain)	$1.0301
eu-central-2 Europe (Zurich)	$1.3180
me-central-1 Middle East (UAE)	$1.2004
sa-east-1 South America (Sao Paulo) Highest	$1.6617
us-east-1 US East (N. Virginia) Lowest	$0.9776
us-east-2 US East (Ohio) Lowest	$0.9776
us-west-2 US West (Oregon) Lowest	$0.9776

Windows — Available in all 20 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-south-2 Asia Pacific (Hyderabad)	$1.5419
ap-southeast-5 Asia Pacific (Malaysia)	$1.5995
ap-south-1 Asia Pacific (Mumbai)	$1.5419
ap-northeast-2 Asia Pacific (Seoul)	$1.5701
ap-southeast-2 Asia Pacific (Sydney)	$1.6391
ap-northeast-1 Asia Pacific (Tokyo)	$1.7858
us-gov-east-1 AWS GovCloud (US-East)	$1.6002
us-gov-west-1 AWS GovCloud (US-West)	$1.6002
ca-central-1 Canada (Central)	$1.4535
eu-central-1 EU (Frankfurt)	$1.5905
eu-west-2 EU (London)	$1.6090
eu-west-3 EU (Paris)	$1.6090
eu-north-1 EU (Stockholm)	$1.4049
eu-south-2 Europe (Spain)	$1.3981
eu-central-2 Europe (Zurich)	$1.6860
me-central-1 Middle East (UAE)	$1.5684
sa-east-1 South America (Sao Paulo) Highest	$2.0297
us-east-1 US East (N. Virginia) Lowest	$1.3456
us-east-2 US East (Ohio) Lowest	$1.3456
us-west-2 US West (Oregon) Lowest	$1.3456

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 g6.2xlarge on Linux is 57% of the on-demand rate, so the instance has to run at least 57% 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.