AWS Amazon EC2

x8i.12xlarge

Part of the X8I Memory Optimized family — High memory-to-vCPU ratio for memory-intensive applications.

Name:xExtreme Memory Optimized88th GenerationiIntel Xeon Scalable12xlarge12 Extra Large

On-demand, Linux

$5.2519/ hr

~$3,833.90/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$2.02493/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −61% vs on-demand rate (us-east-1)

Per unit

$0.1094/ vCPU-hr

$0.0068/GB-hr

Compute

48vCPUs

24 cores • x86_64

Memory

768GB

16.0 GB / vCPU

Network

22.5 Gbps

Baseline: 22.5 Gbps

Storage & EBS

1,875MB/s

Max: 60,000 IOPS

On Google Cloud

The nearest Google Cloud machines to x8i.12xlarge by vCPU and memory, at On-demand Linux rates in Northern Virginia (us-east-1 ↔ us-east4).

Machine	Size	On-demand Linux	vs x8i.12xlarge
x8i.12xlargeThis page · AWS, us-east-1	48 vCPU · 768 GiB	$5.25192/hr	—
m3-megamem-6464 vCPU and 976 GiB for 48 vCPU and 768 GiB, the nearest size up; Intel on both; 24 physical cores vs 32	64 vCPU · 976 GiB	$7.181208/hr	37% more
m4-hypermem-6464 vCPU and 992 GiB for 48 vCPU and 768 GiB, the nearest size up; Intel on both; 24 physical cores vs 32	64 vCPU · 992 GiB	$5.703258/hr	8.6% more
m4n-hypermem-6464 vCPU and 992 GiB for 48 vCPU and 768 GiB, the nearest size up; Intel on both; 24 physical cores vs 32	64 vCPU · 992 GiB	$10.265862/hr	95% more

Matched on vCPU and memory, then CPU vendor, then rate; a larger size is offered only when nothing is the same size. On-demand Linux only: Spot and commitments work differently on the two clouds, so they aren't compared here.

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorIntel Xeon Scalable (Granite Rapids)

Architecturex86_64 (x86_64)

vCPUs / Threads48 vCPUs

Physical Cores24

Clock Speed3.9 GHz

Intel AVX / AVX2AVX & AVX2 Supported

Intel Turbo BoostYes

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,197,605

CoreMark / vCPU24,950.1 / core

FFmpeg Transcoding261 FPS

CoreMark per Dollar228,032 score / $

Cost per vCPU-hr$0.1094

Cost per GB-hr$0.0068

Containers & Kubernetes

EKS Max Pods590 pods

Max ENIs12

IPv4/v6 per ENI50

Total Addressable IPs600 total IPs

CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance22.5 Gbps

Baseline Bandwidth22.5 Gbps

Burst / Peak Bandwidth22.5 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only

Local NVMe DiskNone (EBS only)

EBS Baseline Throughput1875 MB/s

EBS Max Throughput1875 MB/s

EBS Baseline IOPS60,000

EBS Max / Burst IOPS60,000

Dedicated EBS Throughput15000 Mbps

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)

Nitro EnclavesSupported (Isolated security enclaves)

Normalization Factor96

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$5.2519/ hr

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

Highest Price Region

$10.2415/ hr

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

Global Fleet Average

$6.7185/ hr

Across all active regions

Regional Coverage

17regions

Available worldwide

Linux — Available in all 17 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-southeast-5 Asia Pacific (Malaysia)	$6.8539
ap-south-1 Asia Pacific (Mumbai)	$5.4187
ap-northeast-2 Asia Pacific (Seoul)	$7.6154
ap-southeast-1 Asia Pacific (Singapore)	$7.6154
ap-southeast-2 Asia Pacific (Sydney)	$7.6154
ap-northeast-1 Asia Pacific (Tokyo)	$7.6154
us-gov-west-1 AWS GovCloud (US-West)	$6.3024
eu-central-1 EU (Frankfurt)	$7.3529
eu-west-1 EU (Ireland)	$6.3024
eu-south-1 EU (Milan)	$6.6154
eu-west-3 EU (Paris)	$6.6173
eu-north-1 EU (Stockholm)	$5.9894
eu-south-2 Europe (Spain)	$6.3024
sa-east-1 South America (Sao Paulo) Highest	$10.2415
us-east-1 US East (N. Virginia) Lowest	$5.2519
us-east-2 US East (Ohio) Lowest	$5.2519
us-west-2 US West (Oregon) Lowest	$5.2519

Windows — Available in all 17 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-southeast-5 Asia Pacific (Malaysia)	$9.0619
ap-south-1 Asia Pacific (Mumbai)	$7.6267
ap-northeast-2 Asia Pacific (Seoul)	$9.8234
ap-southeast-1 Asia Pacific (Singapore)	$9.8234
ap-southeast-2 Asia Pacific (Sydney)	$9.8234
ap-northeast-1 Asia Pacific (Tokyo)	$9.8234
us-gov-west-1 AWS GovCloud (US-West)	$8.5104
eu-central-1 EU (Frankfurt)	$9.5609
eu-west-1 EU (Ireland)	$8.5104
eu-south-1 EU (Milan)	$8.8234
eu-west-3 EU (Paris)	$8.8253
eu-north-1 EU (Stockholm)	$8.1974
eu-south-2 Europe (Spain)	$8.5104
sa-east-1 South America (Sao Paulo) Highest	$12.4495
us-east-1 US East (N. Virginia) Lowest	$7.4599
us-east-2 US East (Ohio) Lowest	$7.4599
us-west-2 US West (Oregon) Lowest	$7.4599

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 x8i.12xlarge on Linux is 39% of the on-demand rate, so the instance has to run at least 39% 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.