Instances›AWS EC2›r8a›r8a.4xlarge
Compute
vCPUs16
Memory128 GiB
Mem / vCPU8.00 GiB
ProcessorEPYC 9R45 Processor
Clock speedUp to 4.5 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth10,000 Mbps
Throughput1250 MB/s
IOPS40,000
Networking
PerformanceUp to 15 Gigabit
Max ENIs8
IPv6Yes
GPUNone
Family sizes
r8a.medium1 vCPU · 8 GiB
r8a.large2 vCPU · 16 GiB
r8a.xlarge4 vCPU · 32 GiB
r8a.2xlarge8 vCPU · 64 GiB
r8a.4xlarge16 vCPU · 128 GiB
r8a.8xlarge32 vCPU · 256 GiB
r8a.12xlarge48 vCPU · 384 GiB
r8a.16xlarge64 vCPU · 512 GiB
r8a.24xlarge96 vCPU · 768 GiB
r8a.metal-24xl96 vCPU · 768 GiB
r8a.48xlarge192 vCPU · 1536 GiB
r8a.metal-48xl192 vCPU · 1536 GiB
r8a.4xlarge

The r8a.4xlarge is a memory-optimized AWS EC2 instance: 16 vCPU and 128 GiB of memory, 8.00 GiB per vCPU. In the name, "r" stands for RAM, "8" is the generation, "a" marks AMD processors and "4xlarge" is the size within the r8a family. It runs on AMD EPYC 9R45 Processor at Up to 4.5 GHz, and AWS introduced it in November 2025. AWS has since shipped r9g; r9g.4xlarge is the direct replacement at this size. Rackspace Spot's mh.vs1.2xlarge is a like-for-like substitute at 16 vCPU and 128 GiB, $1.28/hr on AWS in US East (N. Virginia), from $0.021/hr on Rackspace Spot.

Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$1.278$0.453$0.021
$1.257 savings
US Central, Chicagono AWS region$0.021
US Central, Dallasno AWS region$0.131
Hong Kong$0.021
Sydney, Australia$0.021
London, UK$0.131
US West, San Jose$0.002
US Central, Dallas 2no AWS region$0.242
When to use it
Good for
  • ●Database instances that keep the working set in RAM
  • ●Graph and search workloads with large indexes
  • ●In-memory caches such as Redis and Memcached
  • ●Workloads that fit inside 128 GiB of RAM
  • ●Parallel work that can occupy 16 vCPU
  • ●Network-heavy services — AWS rates this size at Up to 15 Gigabit
Avoid if
  • ●The working set needs more than 128 GiB of RAM
  • ●CPU-bound work. You are paying for memory this workload will not use.
  • ●More than 8.00 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 16 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
  • ●GPU or FPGA acceleration is needed
$933/mo on AWS on-demand against $15/mo on Rackspace Spot for the 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