Instances›AWS EC2›m6a›m6a.24xlarge
Compute
vCPUs96
Memory384 GiB
Mem / vCPU4.00 GiB
ProcessorEPYC 7R13 Processor
Clock speed3.6 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth30,000 Mbps
Throughput3750 MB/s
IOPS120,000
Networking
Performance37.5 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.24xlarge

The m6a.24xlarge pairs 96 vCPU with 384 GiB of RAM, the 4.00 GiB-per-vCPU ratio that marks a general-purpose instance. In the name, "m" is the general-purpose line, "6" is the generation, "a" marks AMD processors and "24xlarge" 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.24xlarge is the direct replacement at this size, scoring 2,714,420 CoreMark/s against this instance's 1,807,144 — roughly 50% more throughput for the same vCPU count. Spot's node ladder tops out below this size, so m6a.24xlarge becomes 6 × gp.vs2.2xlarge (96 vCPU, 384 GiB combined), 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.24xlarge gives you 96 vCPU and 384 GiB in a single machine. The largest comparable Spot node, gp.vs2.2xlarge, is 16 vCPU and 64 GiB, so the equivalent here is 6 nodes rather than one.

Spot runs as managed Kubernetes, so a 6-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 96 cores and 384 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$4.147$1.163$2.743$1.881$0.246
$3.901 savings
US Central, Chicagono AWS region$0.246
US Central, Dallasno AWS region$0.306
Hong Kong$0.066
Sydney, Australia$5.184$1.904$3.429$2.352$0.966
$4.218 savings
London, UK$4.795$1.730$3.167$2.180$1.326
$3.469 savings
US West, San Jose$4.838$1.782$3.191$2.204$0.906
$3.932 savings
US Central, Dallas 2no AWS region$0.006
US East, N. Virginia 2$4.147$1.163$2.743$1.881$0.906
$3.241 savings
When to use it
Good for
  • ●Web and application servers with mixed CPU and memory demand
  • ●Microservices and container fleets
  • ●Development, staging and CI environments
  • ●Workloads that fit inside 384 GiB of RAM
  • ●Parallel work that can occupy 96 vCPU
  • ●Network-heavy services — AWS rates this size at 37.5 Gigabit
  • ●Anything that shards cleanly across 6 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●Starting a new deployment. m7a.24xlarge is the newer generation at this size.
  • ●The working set needs more than 384 GiB of RAM
  • ●Sustained full-core CPU load. A compute-optimized family costs less per unit of work.
  • ●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 96 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
m6a.24xlarge runs $3,027/mo on AWS on-demand. The 6-node equivalent on Rackspace Spot: $180/mo.
  • 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