AWS EC2 Instances›General Purpose›m8gd›m8gd.24xlarge

Compared with Rackspace Spot

AWSRackspace Spot
Machinem8gd.24xlarge6 × gp.vs2.2xlarge
vCPU9696
Memory384 GiB384 GiB
Local disk3 × 1,900 GB NVMe SSDNone
On-demand / hr$6.516$2.100
Spot / hr$2.240$0.906
Prices in US West, San Jose

Compute

vCPUs96
Memory384 GiB
Mem / vCPU4.00 GiB
ProcessorGraviton4 Processor
Clock speed2.7 GHz
Architecturearm64
GPU0
GPU Wattage0 W
GPU ArchitectureNone
Video Memory0 GiB
FPGA0
ffmpeg FPSN/A
CoreMark / secN/A

Storage

Type3 × 1,900 GB NVMe SSD
Bandwidth30,000 Mbps
Throughput3750 MB/s
IOPS120,000
Base Bandwidth30,000 Mbps
Base Throughput3750 MB/s
Base IOPS120,000
Devices3
NVMe DriveYes
SSDYes
Swap PartitionNo
Local Read IOPS1,609,998
Local Write IOPS805,002

Networking

Performance40 Gigabit
Max ENIs15
IPv6Yes
GPUNone
Placement GroupSupported
TrunkingYes
Branch Interface107
IPs / ENI50
Baseline Bandwidth40 Gbps

NUMA Architecture

Uses NUMANo
Node CountN/A
Max DistanceN/A
Cores / NodeN/A
Threads / NodeN/A
Memory / NodeN/A
L3 Cache / NodeN/A
L3 Cache SharedN/A

AWS Metadata

Instance typem8gd.24xlarge
Full nameM8GD 24xlarge
FamilyGeneral purpose
Variantm8gd
GenerationCurrent
Bare MetalNo
EMR supportYes
DedicatedSupported
Introduced2025-04-21
Family sizes

m8gd.24xlarge

The m8gd.24xlarge is a general-purpose AWS EC2 instance with 96 vCPU and 384 GiB of memory. In US East (N. Virginia), the closest Rackspace Spot server is gp.vs1.2xlarge at 16 vCPU and 64 GiB, so you will need 6 of them to get a total of 96 vCPU and 384 GiB.

Even with 6 servers, Rackspace Spot's on-demand price is about 67% below AWS on-demand and its Spot market price is about 95% below AWS Spot. Rackspace Spot offers managed Kubernetes, so you can run them together in one cluster.

Server comparison caveats
Scale-out match

The AWS m8gd.24xlarge gives you 96 vCPU and 384 GiB in a single machine. The largest comparable Rackspace Spot server, gp.vs2.2xlarge, is 16 vCPU and 64 GiB, so the equivalent here is 6 servers rather than one.

This setup works best for Kubernetes workloads, or for workloads that already sit behind a load balancer, a queue or a scheduler, because they spread across the 6 servers without changes. If it needs all 96 cores and 384 GiB in one process, it does not.

x86_64 only

The AWS m8gd.24xlarge 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, so it is worth testing before you decide how many nodes to run.

No local disk

The AWS m8gd.24xlarge comes with 3 × 1,900 GB NVMe SSD attached to the machine. Rackspace Spot servers 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 attached to your Rackspace Spot server, or object storage, and both are slower to read.

Pricing by region

1 hr

Regions are Rackspace Spot locations.

RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace on-demandRackspace SpotOn-demand price savingsSpot price savings
US East, N. Virginia$5.535$5.042not offerednot offered$1.824$0.246
$3.711 (67%)
$4.796 (95%)
US Central, Chicagono AWS regionn/an/an/a$2.016$0.066n/an/a
US Central, Dallasno AWS regionn/an/an/a$1.938$0.426n/an/a
Hong Kongnot sold heren/an/an/a$2.034$0.066n/an/a
Sydney, Australia$6.956$1.408not offerednot offered$1.914$0.066
$5.042 (72%)
$1.342 (95%)
London, UK$6.418$1.109not offerednot offered$1.734$0.786
$4.684 (73%)
$0.324 (29%)
US West, San Jose$6.516$2.240not offerednot offered$2.100$0.906
$4.415 (68%)
$1.334 (60%)
US Central, Dallas 2no AWS regionn/an/an/a$2.040$0.006n/an/a
US East, N. Virginia 2$5.535$5.042not offerednot offered$2.100$1.146
$3.435 (62%)
$3.896 (77%)

Prices updated 17 Nov 2026.

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 384 GiB of RAM
  • ●Jobs that want 3 × 1,900 GB of local NVMe scratch space
  • ●Network-heavy services (AWS rates this size at 40 Gigabit)
  • ●Anything that shards cleanly across 6 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●The working set needs more than 384 GiB of RAM
  • ●You cannot rebuild x86-only binaries or vendor images for aarch64
  • ●More than 4.00 GiB of RAM per vCPU is needed, since that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 96 vCPU would sit idle.
  • ●GPU or FPGA acceleration is needed
  • ●Sustained full-core CPU load. A compute-optimized family costs less per unit of work.
m8gd.24xlarge is $4,041/mo on AWS on-demand and $1,332/mo on Rackspace Spot on-demand for 6 servers, 67% less. At the Spot market price, the same capacity is $180/mo.
  • Rackspace 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

How much does m8gd.24xlarge cost?

The AWS m8gd.24xlarge costs $5.54/hr on-demand in US East (N. Virginia), about $4,041/mo running 24/7, or $5.04/hr at the AWS Spot price. On Rackspace Spot, 6 × gp.vs2.2xlarge is $1.82/hr on-demand, or $0.246/hr at the Spot price. Rackspace Spot also sells in Chicago and Dallas, where AWS operates no region at all, so those rows have no AWS price to compare against.

How much is m8gd.24xlarge per month?

At 730 hours a month, m8gd.24xlarge in US East (N. Virginia) is $4,041/mo on AWS on-demand, or $3,681/mo at the AWS Spot price. The same capacity on Rackspace Spot (6 × gp.vs2.2xlarge) is $1,332/mo on-demand, or $180/mo at the Spot price. Rackspace Spot prices move with demand, so the Spot figure is a typical rate rather than a fixed one.

How many Rackspace Spot nodes replace one m8gd.24xlarge?

6. The gp.vs2.2xlarge server is 16 vCPU and 64 GiB, and Rackspace Spot's whole VM catalog tops out at 16 vCPU, so covering 96 vCPU and 384 GiB takes 6 of them: 96 vCPU and 384 GiB in total. Per-region fleet sizes differ and are shown in the table.

Is m8gd.24xlarge ARM or x86?

ARM. m8gd.24xlarge runs on AWS Graviton4 Processor, so its binaries and container images are aarch64. Rackspace Spot's gp.vs2.2xlarge is x86-64, which means this is a substitution and not a migration: anything not already built multi-arch has to be rebuilt before it runs. For interpreted stacks that is usually a rebuild of the base image; for anything with native extensions, check them individually.

Does the Rackspace Spot equivalent include local NVMe storage?

No. m8gd.24xlarge ships 3 × 1,900 GB of local NVMe SSD, rated 1,609,998 read IOPS. Rackspace Spot servers are network-backed, so a workload that leans on local disk throughput needs block storage or a re-architecture. Everything else about the match still holds.

What is the difference between m8gd and m9gd?

m9gd is the newer generation. It runs on AWS Graviton5 Processor against m8gd's AWS Graviton4 Processor. On-demand in US East (N. Virginia) the newer size is 9% more expensive. Neither generation changes the Rackspace Spot side: both map to the same Rackspace Spot servers.