AWS Amazon EC2

m8i.96xlarge

Part of the M8I General Purpose family — Balanced compute, memory, and networking for a wide range of workloads.

Name:mGeneral Purpose88th GenerationiIntel Xeon Scalable96xlarge96 Extra Large

On-demand, Linux

$20.3213/ hr

~$14,834.53/mo · lowest in US East (N. Virginia), us-east-1

Savings Plan, Linux

$10.30586/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −49% vs on-demand rate (us-east-1)

Per unit

$0.0529/ vCPU-hr

$0.0132/GB-hr

Compute

384vCPUs

192 cores • x86_64

Memory

1,536GB

4.0 GB / vCPU

Network

100 Gbps

Baseline: 100 Gbps

Storage & EBS

10,000MB/s

Max: 480,000 IOPS

On Google Cloud

The nearest Google Cloud machines to m8i.96xlarge by vCPU and memory, at On-demand Linux rates in Northern Virginia (us-east-1 ↔ us-east4).

Machine	Size	On-demand Linux	vs m8i.96xlarge
m8i.96xlargeThis page · AWS, us-east-1	384 vCPU · 1,536 GiB	$20.32128/hr	—
c4d-highmem-384384 vCPU and 3024 GiB for 384 vCPU and 1536 GiB, the nearest size up; Intel vs AMD	384 vCPU · 3,024 GiB	$23.908269/hr	18% more
z4d-highmem-384-standardlssd384 vCPU and 3024 GiB for 384 vCPU and 1536 GiB, the nearest size up; Intel vs AMD; local disk on z4d-highmem-384-standardlssd only	384 vCPU · 3,024 GiB	$26.168048/hr	29% more
c4d-highmem-384-lssd384 vCPU and 3024 GiB for 384 vCPU and 1536 GiB, the nearest size up; Intel vs AMD; local disk on c4d-highmem-384-lssd only	384 vCPU · 3,024 GiB	$26.538406/hr	31% 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 / Threads384 vCPUs

Physical Cores192

Clock Speed3.9 GHz

Intel AVX / AVX2AVX & AVX2 Supported

Intel Turbo BoostYes

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score8,717,367

CoreMark / vCPU22,701.5 / core

FFmpeg Transcoding309 FPS

CoreMark per Dollar428,977 score / $

Cost per vCPU-hr$0.0529

Cost per GB-hr$0.0132

Containers & Kubernetes

EKS Max Pods1514 pods

Max ENIs24

IPv4/v6 per ENI64

Total Addressable IPs1536 total IPs

CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance100 Gbps

Baseline Bandwidth100 Gbps

Burst / Peak Bandwidth100 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only

Local NVMe DiskNone (EBS only)

EBS Baseline Throughput10000 MB/s

EBS Max Throughput10000 MB/s

EBS Baseline IOPS480,000

EBS Max / Burst IOPS480,000

Dedicated EBS Throughput80000 Mbps

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)

Nitro EnclavesSupported (Isolated security enclaves)

Normalization Factor768

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$20.3213/ hr

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

Highest Price Region

$32.3866/ hr

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

Global Fleet Average

$23.9290/ hr

Across all active regions

Regional Coverage

23regions

Available worldwide

Linux — Available in all 23 regions
Region	On-Demand Price	% vs On-Demand Rate
af-south-1 Africa (Cape Town)	$26.8838
ap-south-2 Asia Pacific (Hyderabad)	$21.3792
ap-southeast-5 Asia Pacific (Malaysia)	$21.5904
ap-south-1 Asia Pacific (Mumbai)	$21.3792
ap-southeast-6 Asia Pacific (New Zealand)	$26.6726
ap-northeast-2 Asia Pacific (Seoul)	$24.9773
ap-southeast-1 Asia Pacific (Singapore)	$25.4016
ap-southeast-2 Asia Pacific (Sydney)	$25.4016
ap-northeast-1 Asia Pacific (Tokyo)	$26.2483
us-gov-east-1 AWS GovCloud (US-East)	$25.6128
us-gov-west-1 AWS GovCloud (US-West)	$25.6128
ca-central-1 Canada (Central)	$22.6502
ca-west-1 Canada West (Calgary)	$22.6502
eu-central-1 EU (Frankfurt)	$24.3437
eu-west-1 EU (Ireland)	$22.6502
eu-west-2 EU (London)	$23.4970
eu-west-3 EU (Paris)	$23.7082
eu-south-2 Europe (Spain)	$22.6502
sa-east-1 South America (Sao Paulo) Highest	$32.3866
us-east-1 US East (N. Virginia) Lowest	$20.3213
us-east-2 US East (Ohio) Lowest	$20.3213
us-west-1 US West (N. California)	$23.7082
us-west-2 US West (Oregon) Lowest	$20.3213

Windows — Available in all 23 regions
Region	On-Demand Price	% vs On-Demand Rate
af-south-1 Africa (Cape Town)	$44.5478
ap-south-2 Asia Pacific (Hyderabad)	$39.0432
ap-southeast-5 Asia Pacific (Malaysia)	$39.2544
ap-south-1 Asia Pacific (Mumbai)	$39.0432
ap-southeast-6 Asia Pacific (New Zealand)	$44.3366
ap-northeast-2 Asia Pacific (Seoul)	$42.6413
ap-southeast-1 Asia Pacific (Singapore)	$43.0656
ap-southeast-2 Asia Pacific (Sydney)	$43.0656
ap-northeast-1 Asia Pacific (Tokyo)	$43.9123
us-gov-east-1 AWS GovCloud (US-East)	$43.2768
us-gov-west-1 AWS GovCloud (US-West)	$43.2768
ca-central-1 Canada (Central)	$40.3142
ca-west-1 Canada West (Calgary)	$40.3142
eu-central-1 EU (Frankfurt)	$42.0077
eu-west-1 EU (Ireland)	$40.3142
eu-west-2 EU (London)	$41.1610
eu-west-3 EU (Paris)	$41.3722
eu-south-2 Europe (Spain)	$40.3142
sa-east-1 South America (Sao Paulo) Highest	$50.0506
us-east-1 US East (N. Virginia) Lowest	$37.9853
us-east-2 US East (Ohio) Lowest	$37.9853
us-west-1 US West (N. California)	$41.3722
us-west-2 US West (Oregon) Lowest	$37.9853

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 m8i.96xlarge on Linux is 51% of the on-demand rate, so the instance has to run at least 51% 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.