Developers Begin Using Apple's Local AI Models in iOS 26

The company touted that with this framework, developers gain access to AI models without worrying about any inference cost. Plus, these local models have capabilities such as guided generation and tool calling built in.

As iOS 26 is rolling out to all users, developers have been updating their apps to include features powered by Apple’s local AI models. Apple’s models are small compared with leading models from OpenAI, Anthropic, Google, or Meta. That is why local-only features largely improve quality of life within these apps rather than introducing major workflow changes.

Below are some of the first apps to tap into Apple’s AI framework.

Lil Artist

The Lil Artist app offers various interactive experiences to help kids learn different skills like creativity, math, and music. Developers Arima Jain and Aman Jain shipped an AI story creator with the iOS 26 update. This allows users to select a character and a theme, with the app generating a story using AI. The text generation in the story is powered entirely by Apple’s on-device model.

Image Credits: Lil Artist

Daylish

The developer of the Daylish app is working on a prototype that automatically suggests emojis for timeline events based on the title for the daily planner app.

MoneyCoach

MoneyCoach, a finance tracking app, now features two capabilities powered by local models. The first shows spending insights — for instance, if you spent more than average on groceries that week. The second feature automatically suggests categories and subcategories for quick entries.

Image Credits: MoneyCoach

LookUp

The word-learning app LookUp has added two new modes using Apple’s local AI models. One is a new learning mode that leverages a local model to create examples for a given word, prompting users to explain the usage of that word in a sentence. The developer is also using on-device models to generate a map view of a word’s origin.

Image Credits: LookUp

Image Credits: LookUp

Tasks

The Tasks app now automatically suggests tags for new entries using local models. It can also detect recurring tasks and schedule them automatically. Users can even dictate tasks, with the app using the local model to break speech into individual tasks without an internet connection.

Image Credits: Tasks

Day One

Day One, the journaling app owned by Automattic, uses Apple’s on-device models to generate highlights, suggest titles for entries, and create reflective prompts encouraging deeper writing based on previous content.

Image Credits: Day One

Crouton

The recipe app Crouton leverages Apple Intelligence to suggest tags for recipes, name timers, and break down text into easy-to-follow cooking steps.

Signeasy

Signeasy, a digital signing app, uses local models to extract key insights from contracts and summarize documents for users before signing.

Dark Noise

Dark Noise, the background sound app, uses Apple’s local models to let users describe a soundscape in words and generate one automatically. Users can then fine-tune the sound by adjusting the levels of individual elements.

Lights Out

Lights Out, an F1 tracking app from developer Shihab Mehboob (creator of Avery and Mammoth), uses on-device AI to summarize live race commentary and provide key takeaways during Grand Prix events.

Capture

The note-taking app Capture uses local AI to suggest categories as users type notes or tasks, improving organization and tagging speed.

Image Credits: Capture

Lumy

The sun and weather-tracking app Lumy now uses AI to provide weather-related suggestions and personalized forecasts.

Image Credits: Lumy

CardPointers

CardPointers, an app for managing credit card benefits, now lets users ask questions about their cards and offers using Apple’s on-device AI. It also provides personalized tips for maximizing rewards.

Image Credits: CardPointers

Guitar Wiz

Guitar Wiz integrates Apple’s Foundation Model framework to explain chords, give advanced learners real-time insights, and provide multilingual support for over 15 languages.

SmartGym

SmartGym uses local AI to convert workout descriptions into step-by-step sets with reps, intervals, and equipment details. It also generates monthly summaries and performance reports.

Stoic

Stoic, a journaling app, uses Apple’s models to provide personalized prompts based on user mood tracking. It also summarizes posts and helps users search and organize past entries.

Image Credits: Stoic

SwingVision

SwingVision helps tennis and pickleball players improve their form through video analysis. The app now uses Apple’s Foundation Models to provide specific, actionable feedback on gameplay.

Zoho

Zoho, the India-based productivity suite, is leveraging Apple’s local models for summarization, translation, and transcription across apps like Notebook and Tables.

TrainFitness

TrainFitness uses on-device models to suggest exercise alternatives when users lack specific equipment, enhancing workout flexibility.

Stuff

Stuff, a to-do list app, includes a new listen mode powered by Apple’s AI models that converts spoken words into individual tasks.

We will continue updating this list as more apps adopt Apple’s on-device AI framework in iOS 26.