AWS EC2 Instances›Memory Optimized›r8ib›r8ib.24xlarge

Compared with Rackspace Spot

AWSRackspace Spot
Machiner8ib.24xlarge6 × mh.vs1.2xlarge
vCPU9696
Memory768 GiB768 GiB
Local diskNoneNone
On-demand / hr$10.042$2.586
Spot / hr$3.699$0.126
Prices in US East, N. Virginia

Compute

vCPUs96
Memory768 GiB
Mem / vCPU8.00 GiB
ProcessorXeon Scalable
Clock speed3.9 GHz
Architecturex86_64
GPU0
GPU Wattage0 W
GPU ArchitectureNone
Video Memory0 GiB
FPGA0
ffmpeg FPS267
CoreMark / sec2,268,967

Storage

TypeEBS only
Bandwidth75,000 Mbps
Throughput9375 MB/s
IOPS360,000
Base Bandwidth75,000 Mbps
Base Throughput9375 MB/s
Base IOPS360,000
Devices0
NVMe DriveNo
SSDNo
Swap PartitionNo

Networking

Performance100 Gigabit
Max ENIs16
IPv6Yes
GPUNone
Placement GroupSupported
TrunkingNo
Branch Interface0
IPs / ENI64
Baseline Bandwidth100 Gbps

NUMA Architecture

Uses NUMAYes
Node Count2
Max Distance15
Cores / Node24
Threads / Node48
Memory / Node380,919 MB
L3 Cache / Node480 MB
L3 Cache SharedYes

AWS Metadata

Instance typer8ib.24xlarge
Full nameR8IB 24xlarge
FamilyMemory optimized
Variantr8ib
GenerationCurrent
Bare MetalNo
EMR supportNo
DedicatedSupported
Introduced2026-04-27
Family sizes

r8ib.24xlarge

The r8ib.24xlarge is a memory-optimized AWS EC2 instance with 96 vCPU and 768 GiB of memory. In US East (N. Virginia), the closest Rackspace Spot server is mh.vs1.2xlarge at 16 vCPU and 128 GiB, so you will need 6 of them to get a total of 96 vCPU and 768 GiB.

Even with 6 servers, Rackspace Spot's on-demand price is about 74% below AWS on-demand and its Spot market price is $0.126/hr against $3.70/hr for AWS Spot. Rackspace Spot offers managed Kubernetes, so you can run them together in one cluster.

Server comparison caveats
Scale-out match

The AWS r8ib.24xlarge gives you 96 vCPU and 768 GiB in a single machine. The largest comparable Rackspace Spot server, mh.vs1.2xlarge, is 16 vCPU and 128 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 768 GiB in one process, it does not.

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$10.042$3.699not offerednot offered$2.586$0.126
$7.456 (74%)
$3.573 (97%)
US Central, Chicagono AWS regionn/an/an/a$2.784$0.126n/an/a
US Central, Dallasno AWS regionn/an/an/a$2.778$0.786n/an/a
Hong Kongnot sold heren/an/an/a$2.964$0.126n/an/a
Sydney, Australianot sold heren/an/an/a$2.946$1.146n/an/a
London, UKnot sold heren/an/an/a$2.520$0.174n/an/a
US West, San Jose$12.050$2.411not offerednot offered$2.640$0.012
$9.410 (78%)
$2.399 (100%)
US Central, Dallas 2no AWS regionn/an/an/a$2.640$1.452n/an/a

Prices updated 17 Nov 2026.

When to use it

Good for
  • ●Large JVM heaps and application servers that hold state
  • ●OLAP and business intelligence query engines
  • ●Real-time analytics over hot datasets
  • ●Workloads that fit inside 768 GiB of RAM
  • ●Parallel work that can occupy 96 vCPU
  • ●Network-heavy services (AWS rates this size at 100 Gigabit)
  • ●Anything that shards cleanly across 6 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●The working set needs more than 768 GiB of RAM
  • ●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, since 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
r8ib.24xlarge is $7,330/mo on AWS on-demand and $1,888/mo on Rackspace Spot on-demand for 6 servers, 74% less. At the Spot market price, the same capacity is $92/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 r8ib.24xlarge cost?

The AWS r8ib.24xlarge costs $10.04/hr on-demand in US East (N. Virginia), about $7,330/mo running 24/7, or $3.70/hr at the AWS Spot price. On Rackspace Spot, 6 × mh.vs1.2xlarge is $2.59/hr on-demand, or $0.126/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 r8ib.24xlarge per month?

At 730 hours a month, r8ib.24xlarge in US East (N. Virginia) is $7,330/mo on AWS on-demand, or $2,700/mo at the AWS Spot price. The same capacity on Rackspace Spot (6 × mh.vs1.2xlarge) is $1,888/mo on-demand, or $92/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 r8ib.24xlarge?

6. The mh.vs1.2xlarge server is 16 vCPU and 128 GiB, and Rackspace Spot's whole VM catalog tops out at 16 vCPU, so covering 96 vCPU and 768 GiB takes 6 of them: 96 vCPU and 768 GiB in total. Per-region fleet sizes differ and are shown in the table.

What is the difference between r8ib and r9g?

r9g is the newer generation. It runs on AWS Graviton5 Processor against r8ib's Intel Xeon Scalable (Granite Rapids). On-demand in US East (N. Virginia) the newer size is 39% cheaper. Neither generation changes the Rackspace Spot side: both map to the same Rackspace Spot servers.

What is a cheaper alternative to r8ib.24xlarge?

Rackspace Spot 6 × mh.vs1.2xlarge (96 vCPU, 768 GiB) is $1,888/mo on-demand or $92/mo at the Spot price, against $7,330/mo on-demand or $2,700/mo at the Spot price for r8ib.24xlarge on AWS in US East (N. Virginia). The trade is real: Rackspace Spot capacity is priced by demand and can be reclaimed when demand rises, and workloads have to be containerized.