AWS EC2 Instances›Storage Optimized›i3›i3.8xlarge

Compared with Rackspace Spot

AWSRackspace Spot
Machinei3.8xlarge2 × mh.vs1.2xlarge
vCPU3232
Memory244 GiB256 GiB
Local disk4 × 1,900 GB NVMe SSDNone
On-demand / hr$2.496$0.862
Spot / hr$1.033$0.042
Prices in US East, N. Virginia

Compute

vCPUs32
Memory244 GiB
Mem / vCPU7.63 GiB
ProcessorXeon E5-2686 v4
Clock speed2.3 GHz
Architecturex86_64
GPU0
GPU Wattage0 W
GPU ArchitectureNone
Video Memory0 GiB
FPGA0
ffmpeg FPS113
CoreMark / sec425,306

Storage

Type4 × 1,900 GB NVMe SSD
Bandwidth7,000 Mbps
Throughput875 MB/s
IOPS32,500
Base Bandwidth7,000 Mbps
Base Throughput875 MB/s
Base IOPS32,500
Devices4
NVMe DriveYes
SSDYes
Swap PartitionNo
Local Read IOPS1,650,000
Local Write IOPS720,000

Networking

Performance10 Gigabit
Max ENIs8
IPv6Yes
GPUNone
Placement GroupSupported
TrunkingNo
Branch Interface0
IPs / ENI30
Baseline Bandwidth12 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 typei3.8xlarge
Full nameI3 High I/O Eight Extra Large
FamilyStorage optimized
Varianti3
GenerationCurrent
Bare MetalNo
EMR supportYes
DedicatedSupported
Introduced2016-11-30
Family sizes

i3.8xlarge

The i3.8xlarge is a storage-optimized AWS EC2 instance with 32 vCPU and 244 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 2 of them to get a total of 32 vCPU and 256 GiB.

Even with 2 servers, Rackspace Spot's on-demand price is about 65% below AWS on-demand and its Spot market price is $0.042/hr against $1.03/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 i3.8xlarge gives you 32 vCPU and 244 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 2 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 2 servers without changes. If it needs all 32 cores and 244 GiB in one process, it does not.

No local disk

The AWS i3.8xlarge comes with 4 × 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$2.496$1.033$1.714$1.210$0.862$0.042
$1.634 (65%)
$0.991 (96%)
US Central, Chicagono AWS regionn/an/an/a$0.928$0.042n/an/a
US Central, Dallasno AWS regionn/an/an/a$0.926$0.262n/an/a
Hong Kong$3.296$0.363$2.258$1.599$0.988$0.042
$2.308 (70%)
$0.321 (88%)
Sydney, Australia$2.992$1.142$2.050$1.452$0.982$0.382
$2.010 (67%)
$0.760 (67%)
London, UK$2.896$1.870$1.982$1.417$0.840$0.058
$2.056 (71%)
$1.812 (97%)
US West, San Jose$2.752$0.853$1.882$1.348$0.880$0.004
$1.872 (68%)
$0.849 (100%)
US Central, Dallas 2no AWS regionn/an/an/a$0.880$0.484n/an/a

Prices updated 17 Nov 2026.

When to use it

Good for
  • ●Data warehousing and log processing
  • ●Distributed file systems and search indexes
  • ●Transactional databases with heavy random I/O
  • ●Workloads that fit inside 244 GiB of RAM
  • ●Jobs that want 4 × 1,900 GB of local NVMe scratch space
  • ●Network-heavy services (AWS rates this size at 10 Gigabit)
  • ●Anything that shards cleanly across 2 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●Starting a new deployment. i4i.8xlarge is the newer generation at this size.
  • ●The working set needs more than 244 GiB of RAM
  • ●The work is single-threaded. Most of these 32 vCPU would sit idle.
  • ●GPU or FPGA acceleration is needed
  • ●Workloads that never touch local disk. The instance-store premium is wasted.
  • ●More than 7.63 GiB of RAM per vCPU is needed, since that ratio is fixed for the whole family
i3.8xlarge is $1,822/mo on AWS on-demand and $629/mo on Rackspace Spot on-demand for 2 servers, 65% less. At the Spot market price, the same capacity is $31/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 i3.8xlarge cost?

The AWS i3.8xlarge costs $2.50/hr on-demand in US East (N. Virginia), about $1,822/mo running 24/7, or $1.03/hr at the AWS Spot price. On Rackspace Spot, 2 × mh.vs1.2xlarge is $0.862/hr on-demand, or $0.042/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 i3.8xlarge per month?

At 730 hours a month, i3.8xlarge in US East (N. Virginia) is $1,822/mo on AWS on-demand, or $754/mo at the AWS Spot price. The same capacity on Rackspace Spot (2 × mh.vs1.2xlarge) is $629/mo on-demand, or $31/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 i3.8xlarge?

2. 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 32 vCPU and 244 GiB takes 2 of them: 32 vCPU and 256 GiB in total. Per-region fleet sizes differ and are shown in the table.

Does the Rackspace Spot equivalent include local NVMe storage?

No. i3.8xlarge ships 4 × 1,900 GB of local NVMe SSD, rated 1,650,000 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.

Is i3.8xlarge still worth using?

For workloads already running on it, yes: it works and it is priced accordingly. For anything new, i4i.8xlarge is the current answer and measures roughly 30% more CoreMark throughput at the same vCPU count. 3 newer generations of the i family have shipped since (i4i, i7i and i8g), which is the signal that matters for infrastructure you expect to keep running.

What is the difference between i3 and i4i?

i4i is the newer generation. It runs on Intel Xeon 8375C (Ice Lake) against i3's Intel Xeon E5-2686 v4 (Broadwell). On the CoreMark figures in this dataset, i4i.8xlarge scores 552,605 per second against i3.8xlarge's 425,306. On-demand in US East (N. Virginia) the newer size is 10% more expensive. Neither generation changes the Rackspace Spot side: both map to the same Rackspace Spot servers.