Ahead-of-time (AOT) compilation for older devices

Will ahead of time compilation stay limited to A17 Pro and M1 class hardware?

  • Docs indicate that AOT compilation is only supported for A17 Pro/M1 and newer.
  • iOS 27 supports iPhone 11 (A13) and newer.
  • AOT can't be used on A13-A16 which is a substantial fraction of active user devices in 2026

Is there a path to AOT on older Apple Silicon chips (A14 and newer) down the line? If not, I am afraid, the impact of AOT will be delayed by 3-4 years until it can be broadly leveraged.

Answered by Engineer in 891726022

Ahead-of-time compilation only compiles for devices that support Apple Intelligence.

Please file a feedback if you require support on older devices along with a description of your use cases.

Ahead-of-time compilation only compiles for devices that support Apple Intelligence.

Please file a feedback if you require support on older devices along with a description of your use cases.

Note that AOT compilation has the biggest impact when using large models. Larger models on older devices can pose some challenges. Independent of model specialization, a large model that consumes too much memory when loaded can degrade system performance or be terminated by the OS. We recommend using a model size that leaves a reasonable buffer for your app and the broader system. You can use os_proc_available_memory() at runtime to query available memory in your app to help make informed decisions about model sizes.

Thank you, I will file a feedback ticket.

Just a note: If Core AI is the way for developers to deploy custom (non-Apple Intelligence) models, it would be consistent that Core AI supports non-Apple Intelligence devices, at least to the same degree as Core ML, so there are concrete reasons to migrate to Core AI.

Without support for A14, A15 and A16, the value of AOT compilation drops significantly in 2026.

Ahead-of-time (AOT) compilation for older devices
 
 
Q