instancefinder
InstanceFinder / AWS / g7e.4xlarge

g7e.4xlarge

EC2 instance type · 16 vCPU · 128 GiB RAM · x86_64

On-demand
$3.9982/hr
Monthly
$2,918.66/mo
vCPU
16
Memory
128 GiB
Comparable 16 vCPU / 128 GiB instances on other clouds: Azure · GCP · OCI
See g7e.4xlarge in the full interactive table →

The g7e.4xlarge is an EC2 instance type with 16 vCPUs and 128 GiB of memory (8 GiB per vCPU), on the x86_64 architecture. On-demand pricing starts at $3.9982/hr ($2,918.66/mo) in us-east-1. It is available in 9 AWS region(s). Not affiliated with AWS.

Pricing — on-demand, us-east-1

Hourly (USD)$3.9982
Monthly (USD, 730 h)$2,918.66
Per vCPU-hour (USD)$0.2499
Per GiB-hour (USD)$0.0312

Full specification

Familyg7e
Size4xlarge
Generation7
Current GenerationYes
Bare MetalNo
Hypervisornitro
Free TierNo
BurstableNo
Dedicated HostsNo
Auto RecoveryNo
HibernationNo
Supported Usageon-demand, spot
Spot SupportedYes
Boot Modeslegacy-bios, uefi
Virt Typeshvm
Root Device Typesebs
Nitro EnclavesYes
Nitro TpmYes
Vcpu16
Cores8
Threads Per Core2
Archx86_64
Clock Ghz2.4
ProcessorIntel
Amd SevNo
Memory Gi B128
Net Perf Text50 Gigabit
Net Peak Gbps50
Net Base Gbps50
Net BurstableNo
Net Cards1
Max Eni8
Ipv4 Per Eni64
Ipv6 Per Eni64
Enarequired
Ena ExpressNo
EfaNo
Encryption In TransitYes
Ebs Optimizeddefault
Ebs Encryptionsupported
Ebs Nvmerequired
Ebs Base Gbps8
Ebs Peak Gbps8
Ebs Base Iops32000
Ebs Peak Iops32000
Ebs Base M Bps1000
Ebs Peak M Bps1000
Storage Gi B1769.51
Storage Typessd
Storage Count1
Storage Nvmerequired
Gpu Count1
Gpu ModelNVIDIA RTX PRO Server 6000
Gpu Mem Gi B96
Valid Cores1, 2, 3, 4, 5, 6, 7, 8
Valid Threads Per Core1, 2
Placement Strategiescluster, partition, spread
Phc SupportNo
Ipv6 SupportedYes
Instance Storage SupportedYes
Nitro Tpm Versions2.0
Gpu Mem Per Gpu Gi B96
Mem Per Vcpu Gi B8
Regionsap-northeast-1, ap-northeast-2, ap-south-1, eu-central-1, eu-north-1, eu-west-2, us-east-1, us-east-2, us-west-2
Region Count9

On-demand price shown for us-east-1, USD, refreshed 2026-07-23T21:04:02+00:00. Prices and availability vary by region and OS — use the interactive table for the rest.