Earl this year, Apple introduced Its base models frame Duration WWDC 2025, which allows developers to use the company’s local models to feed the characteristics in their applications.
The company promoted that with this framework, developers get access to AI models without worrying about any inference cost. In addition, these local models have capacities such as guided generation and integrated tools calls.
As IOS 26 is being implemented for all users, developers have a leg update to include characteristics promoted by Apple’s local models. Apple models are small compared to the main models of OpenAi, Anthrope, Google or Meta. That is why only local characteristics greatly improve the quality of life with thesis applications instead of introducing important changes in the workflow of the application.
Below are some of the first applications that take advantage of Apple’s frame AI.
The Lil Artist application sacrifices several interactive experiences to help children learn different skills such as creativity, mathematics and music. The developer Arima Jain sent a creator of AI stories with the update of iOS 26. This allows users to select a character and a topic, with the application generating a story using AI. The developer said the generation of text in history is driven by the local model.
This developer is working on a prototype for automatic suggestion emojis for timeline events based on the Daily Planner application.
The Moneycoach Finance Monitoring application has two ordered features with local models. First, the application shows information about its expense, as if it spent more than the average on edible for that particular week. The other feature automatically suggests categories and subcategories for an cost element for fast inputs.
This word learning application has added two new ways using Apple AI models. There is a new learning mode, which takes advantage of a local model to create examples corresponding to a word. In addition, the example asks users to explain the use of the word in a sentence.
The developer is also using models on device to generate a map view of the origin of a word.
Like some other applications, the TASKS application implements a function to suggest tags for an entry using automatically local models. You are also using thesis models to detect a recurring task and program it accordingly. And the application allows users to speak some things and use the local model to divide them into several tasks without using the Internet.
The Automatic Property Diary of the Day one is using Apple models to obtain reflexes and suggest titles for entry. The team has also implemented a characteristic to generate indications that push it to immerse more and write more based on what you have already written.
The recipe application is to use Apple Intelligence to suggest tags for a recipe and assign names to the timers. It also uses AI to break down a block of text in easy steps to cook.
The Digital Signature application is using the local Apple models to extract key information from a contract and give users a summary of the document they are signing.
We will continue this list continuously as we discover more applications using Apple local models.
