AWS EC2 Instances›Machine Learning ASIC›dl2q›dl2q.24xlarge

Compute

vCPUs96
Memory768 GiB
Mem / vCPU8.00 GiB
ProcessorXeon Platinum 8259
Clock speed2.5 GHz
Architecturex86_64
GPU8
GPU WattageN/A
GPU ArchitectureN/A
Video Memory128 GiB
FPGA0
ffmpeg FPS179
CoreMark / sec1,295,313

Storage

TypeEBS only
Bandwidth19,000 Mbps
Throughput2375 MB/s
IOPS80,000
Base Bandwidth19,000 Mbps
Base Throughput2375 MB/s
Base IOPS80,000
Devices0
NVMe DriveNo
SSDNo
Swap PartitionNo

Networking

Performance100 Gigabit
Max ENIs15
IPv6Yes
GPUQualcomm AI 100 Accelerators
Placement GroupSupported
TrunkingYes
Branch Interface107
IPs / ENI50
Baseline Bandwidth100 Gbps

NUMA Architecture

Uses NUMAYes
Node Count2
Max Distance21
Cores / Node24
Threads / Node48
Memory / Node382,935 MB
L3 Cache / Node35 MB
L3 Cache SharedYes

AWS Metadata

Instance typedl2q.24xlarge
Full nameDL2Q 24xlarge
FamilyMachine Learning ASIC Instances
Variantdl2q
GenerationCurrent
Bare MetalNo
EMR supportNo
DedicatedSupported
Introduced2023-11-15
Family sizes
dl2q.24xlarge96 vCPU · 768 GiB

dl2q.24xlarge

AWS's dl2q.24xlarge is a machine-learning accelerator instance with 96 vCPU and 768 GiB. Rackspace Spot has no equivalent to offer: the Inferentia and Trainium accelerators are AWS-exclusive silicon with no third-party equivalent.

Rackspace Spot's largest VM tops out at 16 vCPU and 128 GiB, and even that is not the missing piece here. The table below prices what AWS charges; the honest answer on the Rackspace Spot side is that this workload stays where it is.

Server comparison caveats
No equivalent

The AWS dl2q.24xlarge is 8 GPUs (128 GiB VRAM) wired together inside one chassis. The interconnect is what you bought (that is what makes it one accelerator with pooled memory rather than several machines), and Rackspace Spot has nothing that reproduces it. The Rackspace Spot GPU class is built on the NVIDIA A30 (Ampere, 24 GB VRAM), and separate nodes of it on ordinary datacentre networking are not a substitute for a single interconnect-joined node.

Split the job across independent single-GPU nodes only if it is data-parallel with no per-step synchronisation and the model fits one card. Model-parallel work, or anything synchronising gradients every step, does not survive the move. Rackspace Spot sells x86_64 servers up to 16 vCPU, plus one NVIDIA A30 GPU class.

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/anot offerednot offeredn/an/a
US Central, Chicagono AWS regionn/an/an/anot offerednot offeredn/an/a
US Central, Dallasno AWS regionn/an/an/anot offerednot offeredn/an/a
Hong Kongnot sold heren/an/an/anot offerednot offeredn/an/a
Sydney, Australianot sold heren/an/an/anot offerednot offeredn/an/a
London, UKnot sold heren/an/an/anot offerednot offeredn/an/a
US West, San Josenot sold heren/an/an/anot offerednot offeredn/an/a
US Central, Dallas 2no AWS regionn/an/an/anot offerednot offeredn/an/a
US East, N. Virginia 2not sold heren/an/an/anot offerednot offeredn/an/a

Prices updated 18 Nov 2026.

When to use it

Good for
  • ●Workloads already built against the Neuron SDK
  • ●Cost-per-inference optimisation inside AWS
  • ●Inference or training on AWS's own accelerator silicon
  • ●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)
Avoid if
  • ●The working set needs more than 768 GiB of RAM
  • ●The work is single-threaded. Most of these 96 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
  • ●Frameworks that have not been compiled for the Neuron SDK.
  • ●More than 8.00 GiB of RAM per vCPU is needed, since that ratio is fixed for the whole family
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 dl2q.24xlarge cost?

AWS publishes no on-demand price for dl2q.24xlarge 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.

Does Rackspace Spot have an equivalent to dl2q.24xlarge?

No, and it is worth saying so plainly: the Inferentia and Trainium accelerators are AWS-exclusive silicon with no third-party equivalent. Rackspace Spot sells market-priced CPU and GPU capacity, which is a good fit for the batch, web and inference work around this instance, but not for dl2q.24xlarge itself.

What is a cheaper alternative to dl2q.24xlarge?

Not on Rackspace Spot, for the reason above. Within AWS the usual levers are a smaller size in the same family, a reserved or savings-plan commitment, or AWS Spot capacity if the work can tolerate interruption.