On-device ML runtime (Core ML, LiteRT)
Runs trained models on the phone's neural hardware.
In one line
Can run trained AI models on your phone's own chip
Runs trained models on the phone's neural hardware.
Developers ship models with the app and run them on CPU, GPU or the neural chip. NNAPI is deprecated in favour of LiteRT, which targets vendor accelerators.
What it can and can't do
What the user does: Nothing. It happens inside the app when you use a smart feature
It can
- Run models for photos, speech or text using the phone's neural hardware
- Work offline
- Use faster chips on some Android phones, like Qualcomm and MediaTek
It cannot
- Use the Neural Engine on iPhone by choice; the system handles it automatically
- Run without a model the app brought along
- Send your data to a server just because it uses this tool
How it differs between platforms: iPhone uses Core ML, which picks the Neural Engine automatically. Android uses LiteRT, with extra support for some chip makers.
On Android and iPhone
| Android | iPhone | |
|---|---|---|
| Status | Supported | Supported |
| First version | Android 8.1 (API 27) | iOS 11.0 |
| Permission or entitlement | None | None |
| Protection level | none | none |
| How access is granted | none | none |
| What the user sees | None | None |
| How long it lasts | n/a | n/a |
| How to take it back | n/a | n/a |
| Store policy | None listed | None listed |
| API | LiteRT (formerly TensorFlow Lite), LiteRT NPU delegate, NNAPI (deprecated in Android 15), MediaPipe | Core ML, MLX (macOS), Core ML Tools, BNNS Graph |
| Notes | LiteRT Next adds vendor NPU accelerators (Qualcomm, MediaTek). | Core ML uses the Neural Engine automatically. |
Data you get
What comes back: Model output
Shape: object
How often: per run
| Field | Type | Unit | Range | Precision |
|---|---|---|---|---|
tensor | array | float | n/a | n/a |
Technical limits
- Model size and memory limits
The story
What it is
The built in engine that runs trained AI models on the phone's chips.
For you
You never see it. Face unlock, photo search and live camera effects run quickly and privately because a model is running on your phone.
For makers
Makers ship a model inside the app and run it fast on special chips. This keeps data local and avoids server costs, though a model in the app can be copied.
Where you see it
| Type | Example | Apps |
|---|---|---|
| games | A game runs a smart opponent or upscaling model on the phone. | None named |
| creative | A photo app removes a background in real time. | Lightroom, Snapseed |
| health | A fitness app counts reps from the camera with no upload. | None named |
| security | A banking app checks for face spoofing on device. | None named |
| music | A music app recognizes a song or splits vocals. | Shazam |
| ar-vr | An AR app tracks your hands and face live. | Snapchat |
| ads | An ad model on the phone ranks which ads to show without sending data out. | None named |
Risks
- Model theft from the app
- Hidden to the person
Android and iPhone in short
- Android: LiteRT replaces NNAPI and adds chips from Qualcomm and MediaTek.
- iPhone: Core ML uses the Neural Engine automatically.
What the platform says
- Apple: Core ML. Apple describes Core ML as the way to run machine learning models on device with the Neural Engine.
- Google: LiteRT. Google positions LiteRT as its on device runtime for fast, private machine learning.
Good uses and abuse
Legitimate uses
- Vision
- Audio
- Recommendation
Known abuse
- Model theft from the app bundle
Scores
| Score | Value | Meaning |
|---|---|---|
| Sensitivity | 1 of 5 | How revealing the data is |
| Utility | 5 of 5 | How useful it is to honest apps |
| Friction | 0 of 5 | How much the user has to do |
| Fingerprint bits | 0 | Rough identifying entropy, when known |
History
- 2017-06, iPhone iOS 11: Core ML
- 2024-09, Android 15: NNAPI deprecated
- 2024-11, Android LiteRT: TFLite renamed to LiteRT
Related capabilities
Related
- On-device language model (Foundation Models, Gemini Nano Prompt API). Can use a small AI model on your phone, with no internet needed
- Text recognition and visual look up (Live Text, Visual Look Up, ML Kit). Can pick out text in pictures and scan documents on your phone
Sources
How well checked: Based on official documentation.