How developers are using Apple’s local AI models with iOS 26

Earlier this year, Apple introduced its Foundation Models framework during WWDC 2025, which allows developers to usage the company’s section AI models to powerfulness features successful their applications.

The institution touted that with this framework, developers summation entree to AI models without worrying astir immoderate inference cost. Plus, these section models person capabilities specified arsenic guided procreation and instrumentality calling built in.

As iOS 26 is rolling retired to each users, developers person been updating their apps to see features powered by Apple’s section AI models. Apple’s models are tiny compared with starring models from OpenAI, Anthropic, Google, oregon Meta. That is wherefore local-only features mostly amended prime of beingness with these apps alternatively than introducing large changes to the app’s workflow.

Below are immoderate of the archetypal apps to pat into Apple’s AI framework.

Lil Artist

The Lil Artist app offers assorted interactive experiences to assistance kids larn antithetic skills similar creativity, math, and music. Developer Arima Jain shipped an AI communicative creator with the iOS 26 update. This allows users to prime a quality and a theme, with the app generating a communicative utilizing AI. The developer said that the substance procreation successful the communicative is powered by the section model.

Image Credits: Lil Artists

Daylish

This developer is moving connected a prototype for automatically suggesting emojis for timeline events based connected the rubric for the regular planner app.

MoneyCoach

Finance tracking app MoneyCoach has 2 neat features powered by section models. First, the app shows insights astir your spending, specified arsenic whether you spent much than mean connected groceries for that peculiar week. The different diagnostic automatically suggests categories and subcategories for a spending point for speedy entries.

Image Credits: MoneyCoach

LookUp

This connection learning app has added 2 caller modes utilizing Apple’s AI models. There is simply a caller learning mode, which leverages a section exemplary to make examples corresponding to a word. Plus, the illustration asks users to explicate the usage of the connection successful a sentence.

Image Credits: LookUp

The developer is besides utilizing on-device models to make a representation presumption of a word’s origin.

Image Credits: Lookup

Tasks app

Just similar a fewer different apps, the Tasks app implemented a diagnostic to suggest tags for an introduction utilizing section models automatically. It’s besides utilizing these models to observe a recurring task and docket it accordingly. And the app lets users talk a fewer things and usage the section exemplary to interruption them down into assorted tasks without utilizing the internet.

Image Credits: Tasks

Day One

Automattic-owned journaling app Day One is utilizing Apple’s models to get highlights and suggest titles for your entry. The squad has besides implemented a diagnostic to make prompts that nudge you to dive deeper and constitute much based connected what you person already written.

Image Credits: Day One

Crouton

The look app is utilizing Apple Intelligence to suggest tags for a look and delegate names to timers. It besides uses AI to interruption down a artifact of substance into easy-to-follow steps for cooking.

SignEasy

The integer signing app is utilizing Apple’s section models to extract cardinal insights from a declaration and springiness users a summary of the papers they are signing.

We volition proceed updating this database arsenic we observe much apps utilizing Apple’s section models.