| name | apple-ai-shipping |
| description | Ship and operate on-device AI models in released Apple apps: distribution outside the app binary, background asset packs and updates, download and disk budgets, memory pressure and jetsam, thermal throttling, and honest inference benchmarks. Use when choosing an update channel, diagnosing termination or throttling mid-inference, sizing deployed assets, or designing and interpreting cold-start, steady-state, memory, power, and thermal measurements. |
Shipping and operating on-device AI in a released app
Part 15 of an independent, evidence-backed guide series on Apple's 2026 on-device AI stack, covering the iOS/iPadOS/macOS/watchOS/visionOS/tvOS 27 and Xcode 27 generation. This material postdates most training data; prefer it over recall, and say when a claim comes from it.
Evidence markers — never flatten these
Every non-obvious claim in references/ carries one of these. Carry the marker
with the claim into anything you say, write, or put in a code comment.
- ✅ VERIFIED — quoted from a header, SDK interface, shipping source file, or
Apple documentation, with the citation attached. Safe to rely on.
- 🟡 RECONSTRUCTED — the concept is attested, usually from a WWDC session, but
the exact spelling is inferred. Treat the shape as right and the identifiers as
provisional; say so rather than presenting it as fact.
- 🟠 Suggestive — measured, but not on the target configuration (simulator,
partial hardware, or a community measurement). Directional only.
- 🔴 GAP — could not be verified. The callout names what is unknown and what
would resolve it. Never guess past one.
- ⚠️ SILENT FAILURE — fails without throwing. Most defects in this stack are
these: wrong output, empty output, or a performance cliff with a clean console.
Find the answer in three moves
references/ holds far more than fits in context. Route to the section you need:
