AWS EC2 Instances›Compute Optimized›hpc6id›hpc6id.32xlarge

Compared with Rackspace Spot

AWSRackspace Spot
Machinehpc6id.32xlarge30 × ch.vs1.2xlarge
vCPU64480
Memory1024 GiB960 GiB
Local disk4 × 3,800 GB NVMe SSDNone
On-demand / hr--
Spot / hr--

Compute

vCPUs64
Memory1024 GiB
Mem / vCPU16.00 GiB
ProcessorXeon Scalable
Clock speed3.5 GHz
Architecturex86_64
GPU0
GPU Wattage0 W
GPU ArchitectureNone
Video Memory0 GiB
FPGA0
ffmpeg FPS216
CoreMark / sec1,644,610

Storage

Type4 × 3,800 GB NVMe SSD
Bandwidth2,085 Mbps
Throughput260.625 MB/s
IOPS11,000
Base Bandwidth87 Mbps
Base Throughput10.875 MB/s
Base IOPS500
Devices4
NVMe DriveYes
SSDYes
Swap PartitionNo
Local Read IOPS2,146,664
Local Write IOPS1,073,336

Networking

Performance200 Gigabit
Max ENIs2
IPv6Yes
GPUNone
Placement GroupSupported
TrunkingNo
Branch Interface0
IPs / ENI50
Baseline Bandwidth200 Gbps

NUMA Architecture

Uses NUMAYes
Node Count2
Max Distance20
Cores / Node32
Threads / Node32
Memory / Node507,899 MB
L3 Cache / Node54 MB
L3 Cache SharedYes

AWS Metadata

Instance typehpc6id.32xlarge
Full nameHPC6ID 32xlarge
FamilyCompute optimized
Varianthpc6id
GenerationCurrent
Bare MetalNo
EMR supportNo
DedicatedN/A
Introduced2022-11-29
Family sizes
hpc6id.32xlarge64 vCPU · 1024 GiB

hpc6id.32xlarge

The hpc6id.32xlarge is a compute-optimized AWS EC2 instance with 64 vCPU and 1024 GiB of memory. Rackspace Spot's largest server is 16 vCPU and 128 GiB, so matching this instance would take 30 × ch.vs1.2xlarge. That is arithmetically true and operationally absurd.

The Rackspace Spot column below prices that whole fleet, so read it as a scale reference rather than a drop-in replacement: at this size the useful question is what a shard of the workload costs.

Server comparison caveats
No single-node equivalent

The AWS hpc6id.32xlarge is 64 vCPU and 1,024 GiB. The largest comparable Rackspace Spot server is ch.vs1.2xlarge at 16 vCPU and 32 GiB, so matching it would take 30 of them. That maths works out, but 30 nodes is a redesign rather than a migration, because a single block of 1,024 GiB does not survive being split across a network.

If you chose hpc6id.32xlarge because the work genuinely needs 64 cores and 1,024 GiB together (an in-memory database, a large analytics engine, a single big solver), Rackspace Spot has no equivalent. What does fit is everything around it: the application servers, batch workers and CI that talk to that machine, which is usually the larger share of the bill.

No local disk

The AWS hpc6id.32xlarge comes with 4 × 3,800 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. Virginianot sold heren/an/an/a$7.830$1.230n/an/a
US Central, Chicagono AWS regionn/an/an/a$8.310$0.330n/an/a
US Central, Dallasno AWS regionn/an/an/a$8.250$3.930n/an/a
Hong Kongnot sold heren/an/an/a$8.100$0.330n/an/a
Sydney, Australianot sold heren/an/an/a$8.760$1.080n/an/a
London, UKnot sold heren/an/an/a$7.770$1.230n/an/a
US West, San Josenot sold heren/an/an/a$7.670$0.059n/an/a
US Central, Dallas 2no AWS regionn/an/an/a$7.670$3.599n/an/a
US East, N. Virginia 2not sold heren/an/an/a$7.670$3.599n/an/a

Prices updated 17 Nov 2026.

When to use it

Good for
  • ●Video encoding and transcoding
  • ●High-traffic web and API serving
  • ●Scientific modelling and simulation
  • ●Workloads that fit inside 1024 GiB of RAM
  • ●Jobs that want 4 × 3,800 GB of local NVMe scratch space
  • ●Network-heavy services (AWS rates this size at 200 Gigabit)
Avoid if
  • ●The working set needs more than 1024 GiB of RAM
  • ●You want a single-machine Rackspace Spot equivalent. At this size there is not one.
  • ●Memory-hungry applications. A memory-optimized family gives more RAM per dollar.
  • ●More than 16.00 GiB of RAM per vCPU is needed, since that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 64 vCPU would sit idle.
  • ●GPU or FPGA acceleration is needed
Rackspace Spot sells spare capacity at market prices. You pay what the market decides, not a list price.
  • 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 hpc6id.32xlarge cost?

AWS publishes no on-demand price for hpc6id.32xlarge in any of the regions this page covers, because it is not sold there. The specifications and the Rackspace Spot prices below still apply. 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.

Can I replace hpc6id.32xlarge with Rackspace Spot?

Not as a single machine. Rackspace Spot's largest VM shape is 16 vCPU and 128 GiB, so it would take 30 × ch.vs1.2xlarge to reach 64 vCPU and 1024 GiB, and past roughly twenty nodes that stops being a credible substitution. Where the workload does shard (batch, web, queue consumers), a single ch.vs1.2xlarge is the number to compare against; the table's Rackspace Spot column prices the full 30-node fleet.

Does the Rackspace Spot equivalent include local NVMe storage?

No. hpc6id.32xlarge ships 4 × 3,800 GB of local NVMe SSD, rated 2,146,664 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 a cheaper alternative to hpc6id.32xlarge?

Rackspace Spot 30 × ch.vs1.2xlarge is the closest shape; the table above shows current prices by region. Workloads have to be containerized to run on it.