m8a.16xlarge
Amazon EC2 · M8a family
The m8a.16xlarge is a general purpose Amazon EC2 instance type with 64 vCPUs and 256 GiB of memory, running on AMD EPYC 9R45 Processor with 30 Gigabit networking, starting at $3.895 per hour on demand.
- vCPUs
- 64
- memory
- 256 GiB
- processor
- AMD
- on-demand
- $3.895
- spot
- –
- regions
- 10
dedicated
4 GiB per vCPU
x86-64
$2,843/mo · us-east-1
not offered
across 3 areas
m8a.16xlarge price by region
10 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $3.895 |
| US East (Ohio)us-east-2cheapestNorth America | $3.895 |
| US West (Oregon)us-west-2cheapestNorth America | $3.895 |
| Asia Pacific (Hyderabad)ap-south-2Asia | $4.098 |
| Asia Pacific (Mumbai)ap-south-1Asia | $4.098 |
| EU (Ireland)eu-west-1Europe | $4.341 |
| EU (Spain)eu-south-2Europe | $4.341 |
| EU (Frankfurt)eu-central-1Europe | $4.666 |
| AWS GovCloud (US)us-gov-west-1North America | $4.909 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $5.031 |
Specifications
compute
- vCPUs
- 64
- Memory
- 256 GiB
- Memory per vCPU
- 4 GiB
- Processor
- AMD EPYC 9R45 Processor
- CPU vendor
- AMD
- Architecture
- x86-64
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- 30 Gigabit
- Peak bandwidth
- 30 Gbps
aws details
- API name
m8a.16xlarge- Family
- M8a
- Category
- General purpose
- Generation
- Current
- Regions
- 10 (Asia, Europe, North America)
- Cheapest region
- US East (N. Virginia) · $3.895/hr
- Dedicated EBS throughput
- 20000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 128
- Processor features
- AMD Turbo; AVX; AVX2; AVX512
- Spot interruption rate (us-east-1)
- 5-10%
- Spot savings vs on-demand (us-east-1)
- 40%
m8a.16xlarge equivalents on other clouds
closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region
| Provider | Instance | vCPU | Memory | Processor | On-demand | vs m8a.16xlarge |
|---|---|---|---|---|---|---|
| AWS | m8a.16xlarge | 64 | 256 GiB | AMD EPYC 9R45 Processor | $3.895 | – |
| Azure | D64as v5 | 64 | 256 GiB | AMD EPYC 7763v (Milan) | $2.752 | -29% |
| DC64as v5 | 64 | 256 GiB | AMD EPYC 7763v (Milan) | $2.752 | -29% | |
| Google Cloud | n2d-standard-64 | 64 | 256 GiB | AMD Milan, AMD Rome | $2.704 | -31% |
| n4d-standard-64 | 64 | 256 GiB | AMD Turin | $2.71 | -30% | |
| Akamai | G8 Dedicated 256x64 | 64 | 256 GiB | AMD EPYC | $3.36 | -14% |
| Dedicated 256GB56 vCPU (1.1× less) | 56 | 256 GiB | AMD EPYC | $3.456 | -11% | |
| Vultr | vx1-g-64c-256g | 64 | 256 GiB | AMD EPYC | $1.92 | -51% |
| vx1-g-64c-256g-3840s | 64 | 256 GiB | AMD EPYC | $2.446 | -37% |
M8a family sizes
| Size | vCPU | Memory | Local storage | On-demand | Monthly |
|---|---|---|---|---|---|
| m8a.medium | 1 | 4 GiB | – | $0.0609 | $44.43 |
| m8a.large | 2 | 8 GiB | – | $0.1217 | $88.86 |
| m8a.xlarge | 4 | 16 GiB | – | $0.2434 | $178 |
| m8a.2xlarge | 8 | 32 GiB | – | $0.4869 | $355 |
| m8a.4xlarge | 16 | 64 GiB | – | $0.9738 | $711 |
| m8a.8xlarge | 32 | 128 GiB | – | $1.948 | $1,422 |
| m8a.12xlarge | 48 | 192 GiB | – | $2.921 | $2,133 |
| m8a.16xlarge | 64 | 256 GiB | – | $3.895 | $2,843 |
| m8a.24xlarge | 96 | 384 GiB | – | $5.843 | $4,265 |
| m8a.metal-24xl | 96 | 384 GiB | – | $5.843 | $4,265 |
| m8a.48xlarge | 192 | 768 GiB | – | $11.69 | $8,530 |
| m8a.metal-48xl | 192 | 768 GiB | – | $11.69 | $8,530 |
Similar instance types on AWS
other AWS families with a similar shape, cheapest first
m8a.16xlarge FAQ
How much does m8a.16xlarge cost?
m8a.16xlarge costs $3.895 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $2,843 per month. Across 10 regions the Linux on-demand price ranges from $3.895 in US East (N. Virginia) to $5.031 in Asia Pacific (Tokyo). With Windows it costs $6.839 per hour.
How many vCPUs and how much memory does m8a.16xlarge have?
m8a.16xlarge has 64 vCPUs and 256 GiB of memory (4 GiB per vCPU), running on AMD EPYC 9R45 Processor. It is a general purpose instance type in the M8a family.
What are the equivalents of m8a.16xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture and instance class are on Azure, D64as v5 (64 vCPU, 256 GiB, $2.752/hour in East US); on Google Cloud, n2d-standard-64 (64 vCPU, 256 GiB, $2.704/hour in Iowa); on Akamai, G8 Dedicated 256x64 (64 vCPU, 256 GiB, $3.36/hour in Newark, NJ); on Vultr, vx1-g-64c-256g (64 vCPU, 256 GiB, $1.92/hour in New Jersey).