AWS Amazon EC2

m6a.48xlarge

Part of the M6A General Purpose family — Balanced compute, memory, and networking for a wide range of workloads.

Name:mGeneral Purpose66th GenerationaAMD EPYC48xlarge48 Extra Large

On-demand, Linux

$5.3328/ hr

~$3,892.94/mo · lowest in Asia Pacific (Hyderabad), ap-south-2

Savings Plan, Linux

$2.68013/ hr

From, with a 3-year Compute Savings Plan, No Upfront: −50% vs on-demand rate (ap-south-1)

Per unit

$0.0278/ vCPU-hr

$0.0069/GB-hr

Compute

192vCPUs

96 cores • x86_64

Memory

768GB

4.0 GB / vCPU

Network

50 Gbps

Baseline: 50 Gbps

Storage & EBS

5,000MB/s

Max: 240,000 IOPS

On Google Cloud

The nearest Google Cloud machines to m6a.48xlarge by vCPU and memory, at On-demand Linux rates in Northern Virginia (us-east-1 ↔ us-east4).

Machine	Size	On-demand Linux	vs m6a.48xlarge
m6a.48xlargeThis page · AWS, us-east-1	192 vCPU · 768 GiB	$8.2944/hr	—
n2d-standard-224224 vCPU and 896 GiB for 192 vCPU and 768 GiB, the nearest size up; AMD on both; 96 physical cores vs 112	224 vCPU · 896 GiB	$10.65792/hr	28% more
c4d-highmem-192192 vCPU and 1512 GiB for 192 vCPU and 768 GiB, the nearest size up; AMD on both	192 vCPU · 1,512 GiB	$11.954135/hr	44% more
z4d-highmem-192-standardlssd192 vCPU and 1512 GiB for 192 vCPU and 768 GiB, the nearest size up; AMD on both; local disk on z4d-highmem-192-standardlssd only	192 vCPU · 1,512 GiB	$13.084024/hr	58% 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

ProcessorAMD EPYC 7R13 Processor

Architecturex86_64 (x86_64)

vCPUs / Threads192 vCPUs

Physical Cores96

Clock Speed3.6 GHz

Intel AVX / AVX2No

Intel Turbo BoostNo

Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score3,589,456

CoreMark / vCPU18,695.1 / core

FFmpeg Transcoding248 FPS

CoreMark per Dollar673,090 score / $

Cost per vCPU-hr$0.0278

Cost per GB-hr$0.0069

Containers & Kubernetes

EKS Max Pods737 pods

Max ENIs15

IPv4/v6 per ENI50

Total Addressable IPs750 total IPs

CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance50 Gbps

Baseline Bandwidth50 Gbps

Burst / Peak Bandwidth50 Gbps

Enhanced NetworkingYes

EFA SupportNo

IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only

Local NVMe DiskNone (EBS only)

EBS Baseline Throughput5000 MB/s

EBS Max Throughput5000 MB/s

EBS Baseline IOPS240,000

EBS Max / Burst IOPS240,000

Dedicated EBS Throughput40000 Mbps

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)

Nitro EnclavesSupported (Isolated security enclaves)

Normalization Factor384

Generation StatusCurrent Generation (Recommended)

Rates by region

Live on-demand rates across all global AWS cloud regions

Lowest Price Region

$5.3328/ hr

Asia Pacific (Mumbai) (ap-south-1)

Highest Price Region

$13.2192/ hr

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

Global Fleet Average

$9.2040/ hr

Across all active regions

Regional Coverage

16regions

Available worldwide

Linux — Available in all 16 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-south-2 Asia Pacific (Hyderabad) Lowest	$5.3328
ap-south-1 Asia Pacific (Mumbai) Lowest	$5.3328
ap-southeast-1 Asia Pacific (Singapore)	$10.3680
ap-southeast-2 Asia Pacific (Sydney)	$10.3680
ap-northeast-1 Asia Pacific (Tokyo)	$10.7136
ca-central-1 Canada (Central)	$9.2448
eu-central-1 EU (Frankfurt)	$9.9360
eu-west-1 EU (Ireland)	$9.2448
eu-west-2 EU (London)	$9.5904
eu-south-1 EU (Milan)	$9.6768
eu-west-3 EU (Paris)	$9.6768
sa-east-1 South America (Sao Paulo) Highest	$13.2192
us-east-1 US East (N. Virginia)	$8.2944
us-east-2 US East (Ohio)	$8.2944
us-west-1 US West (N. California)	$9.6768
us-west-2 US West (Oregon)	$8.2944

Windows — Available in all 16 regions
Region	On-Demand Price	% vs On-Demand Rate
ap-south-2 Asia Pacific (Hyderabad) Lowest	$14.1648
ap-south-1 Asia Pacific (Mumbai) Lowest	$14.1648
ap-southeast-1 Asia Pacific (Singapore)	$19.2000
ap-southeast-2 Asia Pacific (Sydney)	$19.2000
ap-northeast-1 Asia Pacific (Tokyo)	$19.5456
ca-central-1 Canada (Central)	$18.0768
eu-central-1 EU (Frankfurt)	$18.7680
eu-west-1 EU (Ireland)	$18.0768
eu-west-2 EU (London)	$18.4224
eu-south-1 EU (Milan)	$18.5088
eu-west-3 EU (Paris)	$18.5088
sa-east-1 South America (Sao Paulo) Highest	$22.0512
us-east-1 US East (N. Virginia)	$17.1264
us-east-2 US East (Ohio)	$17.1264
us-west-1 US West (N. California)	$18.5088
us-west-2 US West (Oregon)	$17.1264

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 Asia Pacific (Mumbai) (ap-south-1), the 3-year Compute Savings Plan rate (No Upfront) for m6a.48xlarge on Linux is 50% of the on-demand rate, so the instance has to run at least 50% 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.