Instances›AWS EC2›r9g›r9g.metal-48xl
Compute
vCPUs192
Memory1536 GiB
Mem / vCPU8.00 GiB
ProcessorGraviton5 Processor
Clock speed3.3 GHz
Architecturearm64
Storage
TypeEBS only
Bandwidth72,000 Mbps
Throughput9000 MB/s
IOPS288,000
Networking
Performance100 Gigabit
Max ENIs24
IPv6Yes
GPUNone
Family sizes
r9g.medium1 vCPU · 8 GiB
r9g.large2 vCPU · 16 GiB
r9g.xlarge4 vCPU · 32 GiB
r9g.2xlarge8 vCPU · 64 GiB
r9g.4xlarge16 vCPU · 128 GiB
r9g.8xlarge32 vCPU · 256 GiB
r9g.12xlarge48 vCPU · 384 GiB
r9g.16xlarge64 vCPU · 512 GiB
r9g.24xlarge96 vCPU · 768 GiB
r9g.48xlarge192 vCPU · 1536 GiB
r9g.metal-48xl192 vCPU · 1536 GiB
r9g.metal-48xl

r9g.metal-48xl is AWS's memory-optimized EC2 size at 192 vCPU and 1536 GiB. In the name, "r" stands for RAM, "9" is the generation, "g" marks AWS Graviton (ARM) processors and "metal-48xl" is the size within the r9g family. It runs on AWS Graviton5 Processor at 3.3 GHz, and AWS introduced it in August 2026. r9g is the current generation of the r family, so there is no newer AWS size to migrate to. The closest Spot shape is mh.vs1.2xlarge at 16 vCPU, so this instance maps to 12 of them — 192 vCPU and 1536 GiB across the fleet, $12.33/hr on AWS in US East (N. Virginia), from $0.252/hr on Rackspace Spot. 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

r9g.metal-48xl gives you 192 vCPU and 1,536 GiB in a single machine. The largest comparable Spot node, mh.vs1.2xlarge, is 16 vCPU and 128 GiB, so the equivalent here is 12 nodes rather than one.

Spot runs as managed Kubernetes, so a 12-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 192 cores and 1,536 GiB in one process, it does not.

x86_64 onlyr9g.metal-48xl is Graviton (arm64) and Rackspace Spot has no arm64 nodes, so you'd be moving to x86. You'll need x86 builds of your images, and per-core speed differs between the chips — worth testing before you decide how many nodes to run.
Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$12.328$2.210$0.252
$12.076 savings
US Central, Chicagono AWS region$0.252
US Central, Dallasno AWS region$1.572
Hong Kong$0.252
Sydney, Australia$0.252
London, UK$1.572
US West, San Jose$0.024
US Central, Dallas 2no AWS region$2.904
When to use it
Good for
  • ●OLAP and business intelligence query engines
  • ●Real-time analytics over hot datasets
  • ●Database instances that keep the working set in RAM
  • ●Workloads that fit inside 1536 GiB of RAM
  • ●Parallel work that can occupy 192 vCPU
  • ●Network-heavy services — AWS rates this size at 100 Gigabit
  • ●Anything that shards cleanly across 12 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●The working set needs more than 1536 GiB of RAM
  • ●You cannot rebuild x86-only binaries or vendor images for aarch64
  • ●Local NVMe or instance-store disk is a hard requirement
  • ●GPU or FPGA acceleration is needed
  • ●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
Stop overpaying AWS. This compute costs $9,000/mo on AWS vs $184/mo on Rackspace Spot.
  • 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