Instances›AWS EC2›m8gd›m8gd.metal-48xl
Compute
vCPUs192
Memory768 GiB
Mem / vCPU4.00 GiB
ProcessorGraviton4 Processor
Clock speed2.7 GHz
Architecturearm64
Storage
Type6 × 1,900 GB NVMe SSD
Bandwidth40,000 Mbps
Throughput5000 MB/s
IOPS240,000
Networking
Performance50 Gigabit
Max ENIs15
IPv6Yes
GPUNone
Family sizes
m8gd.medium1 vCPU · 4 GiB
m8gd.large2 vCPU · 8 GiB
m8gd.xlarge4 vCPU · 16 GiB
m8gd.2xlarge8 vCPU · 32 GiB
m8gd.4xlarge16 vCPU · 64 GiB
m8gd.8xlarge32 vCPU · 128 GiB
m8gd.12xlarge48 vCPU · 192 GiB
m8gd.16xlarge64 vCPU · 256 GiB
m8gd.24xlarge96 vCPU · 384 GiB
m8gd.metal-24xl96 vCPU · 384 GiB
m8gd.48xlarge192 vCPU · 768 GiB
m8gd.metal-48xl192 vCPU · 768 GiB
m8gd.metal-48xl

m8gd.metal-48xl is AWS's general-purpose EC2 size at 192 vCPU and 768 GiB. In the name, "m" is the general-purpose line, "8" is the generation, "gd" marks AWS Graviton (ARM) processors and local NVMe storage and "metal-48xl" is the size within the m8gd family. It runs on AWS Graviton4 Processor at 2.7 GHz, and AWS introduced it in April 2025. AWS has since shipped m9gd; m9gd.metal-48xl is the direct replacement at this size. The closest Spot shape is gp.vs2.2xlarge at 16 vCPU, so this instance maps to 12 of them — 192 vCPU and 768 GiB across the fleet, $11.07/hr on AWS in US East (N. Virginia), from $0.492/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 qualityVirtualised, not bare metal

m8gd.metal-48xl is a full physical server — no virtualisation layer in the way, direct access to the hardware, and a socket count that licensing can verify.

Rackspace Spot no longer sells bare metal; everything in the catalog is a virtual machine. You get the same cores and memory (12 × gp.vs2.2xlarge, 192 vCPU, 768 GiB), but not the dedicated hardware. If you picked m8gd.metal-48xl because you needed the real machine — nested virtualisation, per-socket licensing, low-level profiling — this is not a replacement at any price. If you picked it because it is the biggest m8gd, it is the same compute for a lot less.

Runs as a fleetNo single Spot node has 192 vCPU; the largest comparable one has 16. So this runs as 12 nodes. That works if your workload already spreads across machines, and doesn't if one process needs all the cores together.
x86_64 onlym8gd.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.
No local diskm8gd.metal-48xl comes with 6 × 1,900 GB NVMe SSD attached to the machine. Spot nodes use network storage only, so that disk doesn't come with it. If you were using it as fast scratch space, you'd move to a persistent volume or object storage, which are slower to read.
Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$11.071$3.021$0.492
$10.579 savings
US Central, Chicagono AWS region$0.492
US Central, Dallasno AWS region$0.612
Hong Kong$0.132
Sydney, Australia$13.912$1.391$1.932
$11.980 savings
London, UK$12.835$1.284$2.652
$10.183 savings
US West, San Jose$13.031$2.426$1.812
$11.219 savings
US Central, Dallas 2no AWS region$0.012
US East, N. Virginia 2$11.071$3.021$1.812
$9.259 savings
When to use it
Good for
  • ●Small to mid-size relational databases
  • ●Backend services with no single dominant resource
  • ●Queue workers and scheduled jobs
  • ●Workloads that fit inside 768 GiB of RAM
  • ●Jobs that want 6 × 1,900 GB of local NVMe scratch space
  • ●Network-heavy services — AWS rates this size at 50 Gigabit
  • ●Anything that shards cleanly across 12 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●The working set needs more than 768 GiB of RAM
  • ●You cannot rebuild x86-only binaries or vendor images for aarch64
  • ●You need dedicated hardware. Rackspace Spot sells virtualised compute only.
  • ●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 192 vCPU would sit idle.
$8,082/mo on AWS on-demand against $359/mo on Rackspace Spot for the 12-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