inf1.24xlarge is AWS's machine-learning accelerator EC2 size at 96 vCPU and 192 GiB. In the name, "inf" is Inferentia, AWS's inference silicon, "1" is the generation and "24xlarge" is the size within the inf1 family. It runs on Intel Xeon Platinum 8275CL (Cascade Lake) at 3.0 GHz, and AWS introduced it in December 2019. AWS has since shipped inf2; inf2.24xlarge is the direct replacement at this size, scoring 1,914,734 CoreMark/s against this instance's 1,539,880 — roughly 24% more throughput for the same vCPU count. Rackspace Spot has no equivalent to offer: the Inferentia and Trainium accelerators are AWS-exclusive silicon with no third-party equivalent. 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 Spot side is that this workload stays where it is.
Match qualityNo equivalent
inf1.24xlarge is Machine Learning ASIC hardware. That accelerator has no counterpart in the Rackspace Spot catalog, and nothing in it emulates one at a speed worth paying for — this is a genuine no-match, not a weak one.
Rackspace Spot sells x86_64 Kubernetes nodes up to 16 vCPU, plus one NVIDIA A30 GPU class. What does move is the CPU half of the pipeline built around the accelerator: ingest, pre- and post-processing, orchestration, and the serving front end. On most accelerator workloads that tier runs continuously while the accelerator itself is duty-cycled, which is where the bill actually accumulates.
Pricing by region
1 hr
Region
AWS on-demand
AWS Spot
1-yr Reserved
3-yr Reserved
Rackspace Spot
You save
US East, N. Virginia
$4.721
$0.810
$2.974
$2.269
US Central, Chicago
no AWS region
US Central, Dallas
no AWS region
Hong Kong
$7.274
$4.583
$3.496
Sydney, Australia
$5.902
$0.833
$3.718
$2.836
London, UK
$5.530
$0.572
$3.484
$2.658
US West, San Jose
$5.671
$0.567
$3.573
$2.725
US Central, Dallas 2
no AWS region
US East, N. Virginia 2
$4.721
$0.810
$2.974
$2.269
When to use it
Good for
●Cost-per-inference optimisation inside AWS
●Inference or training on AWS's own accelerator silicon
●Workloads already built against the Neuron SDK
●Workloads that fit inside 192 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 192 GiB of RAM
●Frameworks that have not been compiled for the Neuron SDK.
●More than 2.00 GiB of RAM per vCPU is needed — 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
●GPU or FPGA acceleration is needed
Rackspace Spot sells spare capacity at market prices. You pay what the market decides, not a list price.
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.
