g7.8xlargevsg7e.8xlarge

g7.8xlarge is 22% cheaper than g7e.8xlarge on demand in US East (N. Virginia), saving $862.86 a month.

At a glanceg7.8xlargeg7e.8xlarge
On-demand$4.086/hr22% less$5.268/hr
Lowest rate$0.7699/hr68% lessSpot, can be interrupted$2.375/hrSpot, can be interrupted
Size32 vCPUs, 128 GiB32 vCPUs, 256 GiB
ProcessorIntel Xeon Scalable (Granite Rapids)Intel Xeon Scalable (Emerald Rapids)
Architecturex86_64x86_64

Prices in US East (N. Virginia)

“Off” is the discount against each type’s own on-demand price. Linux, USD per hour.

Optiong7.8xlargeg7e.8xlargeg7e.8xlarge vs g7.8xlarge
On-demandPay by the hour$4.086$5.268▲ 29%
SpotCan be interrupted81% off$0.769955% off$2.375▲ 208%
1-yr savings planHourly commitment21% off$3.21821% off$4.149▲ 29%
3-yr savings planHourly commitment46% off$2.20742% off$3.072▲ 39%

Key differences

The biggest lead each one has.

Where g7.8xlarge leads
On-demand price$4.086 vs $5.268 per hour
22% cheaper
Physical cores32 vs 16
2× higher
Max network interfaces10 vs 8
25% higher
Where g7e.8xlarge leads
GPU memory96 GB vs 32 GB
3× higher
Memory (GiB)256 vs 128
2× higher

Specs

14 of 44 specs differ. Those are in bold.

Compute6 of 10 differg7.8xlargeg7e.8xlarge
vCPUs3232
Physical cores3216
Threads per core12
Architecturex86_64x86_64
ProcessorIntel Xeon Scalable (Granite Rapids)Intel Xeon Scalable (Emerald Rapids)
CPU makerIntelIntel
Clock speed3.9 GHz3.2 GHz
Sustained clock3.9 GHz2.4 GHz
Processor featuresIntel AMX; Intel AVX; Intel AVX2; Intel AVX512; Intel TurboIntel AMX
BurstableNoNo
Memory1 of 1 differg7.8xlargeg7e.8xlarge
Memory (GiB)128256
Accelerators2 of 3 differg7.8xlargeg7e.8xlarge
GPUs11
GPU1 × NVIDIA RTX PRO 45001 × NVIDIA RTX PRO Server 6000
GPU memory32 GB96 GB
Networking1 of 8 differg7.8xlargeg7e.8xlarge
Network100 Gigabit100 Gigabit
Network baseline100 Gbps100 Gbps
Network peak100 Gbps100 Gbps
Enhanced networkingYes (ENA)Yes (ENA)
EFAYesYes
IPv6YesYes
Max network interfaces108
IPv4 addresses per interface6464
Storage2 of 12 differg7.8xlargeg7e.8xlarge
Storage1x930 GB NVMe SSD1 x 1900 NVMe SSD
Local disks1 × 930 GB SSD1 × 1,900 GB SSD
EBS optimizedYesYes
EBS over NVMeRequiredRequired
EBS throughput16000 Mbps16000 Mbps
EBS baseline bandwidth16,000 Mbps16,000 Mbps
EBS max bandwidth16,000 Mbps16,000 Mbps
EBS baseline throughput2,000 MB/s2,000 MB/s
EBS max throughput2,000 MB/s2,000 MB/s
EBS baseline IOPS64,00064,000
EBS max IOPS64,00064,000
Max EBS volumes3232
Instance details2 of 10 differg7.8xlargeg7e.8xlarge
Familyg7g7e
CategoryGPU instanceGPU instance
Current generationYesYes
Normalization factor1.621523811.566473988
Bare metalNoNo
HypervisorNitroNitro
Placement groupsCluster, Partition, SpreadCluster, Partition, Spread
HibernationNoNo
Nitro EnclavesYesYes
Boot modesLegacy BIOS, UEFILegacy BIOS, UEFI

On-demand prices by region

Cheapest for g7.8xlarge first. Linux, USD per hour.

Regiong7.8xlargeg7e.8xlargeDifference
US East (N. Virginia)Used in summaryus-east-1$4.086$5.268▲ 29%
US East (Ohio)us-east-2$4.086$5.268▲ 29%
US West (Oregon)us-west-2$4.086$5.268▲ 29%
Europe (Spain)eu-south-2$4.291$5.551▲ 29%
EU (Stockholm)eu-north-1$4.334$7.60▲ 75%
Asia Pacific (Mumbai)ap-south-1$4.907$8.605▲ 75%
EU (Frankfurt)eu-central-1$5.11$8.959▲ 75%
EU (London)eu-west-2$6.198$9.156▲ 48%

Keep exploring

Each type’s own page, and how it compares with others.

g7.8xlargeGPU instance, g7 family
g7.8xlarge prices and specsEvery size in the g7 family

Compare g7.8xlarge with

g6.8xlarge
g7e.8xlargeGPU instance, g7e family
g7e.8xlarge prices and specsEvery size in the g7e family

Compare g7e.8xlarge with

g6e.8xlarge

Pay the committed rate, with commitment protection

The best committed rate on these two is 42–46% below on-demand. Connect your cloud accounts to unlock greater savings with commitment protection.

Connect AWS account

AWS EC2 Linux prices in USD. Monthly figures use 730 hours. Prices last updated 12 Nov 2026.