Instances›AWS EC2›inf1›inf1.6xlarge
Compute
vCPUs24
Memory48 GiB
Mem / vCPU2.00 GiB
ProcessorXeon Platinum 8275CL
Clock speed3.0 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth4,750 Mbps
Throughput593.75 MB/s
IOPS20,000
Networking
Performance25 Gigabit
Max ENIs8
IPv6Yes
GPUNone
Family sizes
inf1.xlarge4 vCPU · 8 GiB
inf1.2xlarge8 vCPU · 16 GiB
inf1.6xlarge24 vCPU · 48 GiB
inf1.24xlarge96 vCPU · 192 GiB
inf1.6xlarge

The inf1.6xlarge pairs 24 vCPU with 48 GiB of RAM, the 2.00 GiB-per-vCPU ratio that marks a machine-learning accelerator instance. In the name, "inf" is Inferentia, AWS's inference silicon, "1" is the generation and "6xlarge" 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. 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

inf1.6xlarge 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
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$1.180$0.223$0.744$0.567
US Central, Chicagono AWS region
US Central, Dallasno AWS region
Hong Kong$1.819$1.146$0.874
Sydney, Australia$1.475$0.243$0.930$0.709
London, UK$1.382$0.157$0.871$0.664
US West, San Jose$1.418$0.142$0.893$0.681
US Central, Dallas 2no AWS region
US East, N. Virginia 2$1.180$0.223$0.744$0.567
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 48 GiB of RAM
  • ●Parallel work that can occupy 24 vCPU
  • ●Network-heavy services — AWS rates this size at 25 Gigabit
Avoid if
  • ●The working set needs more than 48 GiB of RAM
  • ●GPU or FPGA acceleration is needed
  • ●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 24 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
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.
Build your Cloudspace
Frequently asked questions