Instances›AWS EC2›m6a›m6a.32xlarge
Compute
vCPUs128
Memory512 GiB
Mem / vCPU4.00 GiB
ProcessorEPYC 7R13 Processor
Clock speed3.6 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth40,000 Mbps
Throughput5000 MB/s
IOPS160,000
Networking
Performance50 Gigabit
Max ENIs15
IPv6Yes
GPUNone
Family sizes
m6a.large2 vCPU · 8 GiB
m6a.xlarge4 vCPU · 16 GiB
m6a.2xlarge8 vCPU · 32 GiB
m6a.4xlarge16 vCPU · 64 GiB
m6a.8xlarge32 vCPU · 128 GiB
m6a.12xlarge48 vCPU · 192 GiB
m6a.16xlarge64 vCPU · 256 GiB
m6a.24xlarge96 vCPU · 384 GiB
m6a.32xlarge128 vCPU · 512 GiB
m6a.48xlarge192 vCPU · 768 GiB
m6a.metal192 vCPU · 768 GiB
m6a.32xlarge

The m6a.32xlarge is a general-purpose AWS EC2 instance: 128 vCPU and 512 GiB of memory, 4.00 GiB per vCPU. In the name, "m" is the general-purpose line, "6" is the generation, "a" marks AMD processors and "32xlarge" is the size within the m6a family. It runs on AMD EPYC 7R13 Processor at 3.6 GHz, and AWS introduced it in November 2021. AWS has since shipped m7a, m8a and m9g; m7a.32xlarge is the direct replacement at this size, scoring 4,116,638 CoreMark/s against this instance's 2,624,430 — roughly 57% more throughput for the same vCPU count. No single Spot node covers 128 vCPU and 512 GiB, so the equivalent is a fleet: 8 × gp.vs2.2xlarge, 128 vCPU and 512 GiB in total, about 94% below the US East (N. Virginia) on-demand rate. Spot delivers compute as managed Kubernetes, so a node pool of that size is the native shape of the answer rather than a workaround — provided the workload scales horizontally.

Match qualityScale-out match

m6a.32xlarge gives you 128 vCPU and 512 GiB in a single machine. The largest comparable Spot node, gp.vs2.2xlarge, is 16 vCPU and 64 GiB, so the equivalent here is 8 nodes rather than one.

Spot runs as managed Kubernetes, so a 8-node pool is the normal way to run things rather than a workaround. If your workload already sits behind a load balancer, a queue or a scheduler, it spreads across them without changes. If it needs all 128 cores and 512 GiB in one process, it does not.

Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$5.530$2.173$3.658$2.508$0.328
$5.202 savings
US Central, Chicagono AWS region$0.328
US Central, Dallasno AWS region$0.408
Hong Kong$0.088
Sydney, Australia$6.912$3.074$4.572$3.135$1.288
$5.624 savings
London, UK$6.394$1.908$4.223$2.907$1.768
$4.626 savings
US West, San Jose$6.451$1.243$4.255$2.939$1.208
$5.243 savings
US Central, Dallas 2no AWS region$0.008
US East, N. Virginia 2$5.530$2.173$3.658$2.508$1.208
$4.322 savings
When to use it
Good for
  • ●Development, staging and CI environments
  • ●Small to mid-size relational databases
  • ●Backend services with no single dominant resource
  • ●Workloads that fit inside 512 GiB of RAM
  • ●Parallel work that can occupy 128 vCPU
  • ●Network-heavy services — AWS rates this size at 50 Gigabit
  • ●Anything that shards cleanly across 8 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●Starting a new deployment. m7a.32xlarge is the newer generation at this size.
  • ●The working set needs more than 512 GiB of RAM
  • ●More than 4.00 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 128 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
  • ●GPU or FPGA acceleration is needed
$4,037/mo on AWS on-demand against $239/mo on Rackspace Spot for the 8-node equivalent — market-priced, not list-priced.
  • Spot sells spare capacity at market prices. It is the cheapest compute on the internet.
  • Prices are set by supply and demand. You pay what the market decides.
  • Compute is delivered as fully managed Kubernetes. All infrastructure is taken care of.
  • Egress costs $0.01/GB after the free allowance. AWS charges $0.09/GB.
Build your Cloudspace
Frequently asked questions