docs/en/run/android/install.mdx
import Feedback from "/snippets/page-feedback.mdx";
Add the GenieX SDK to an Android Studio project so your app can pull weights from Hugging Face / Qualcomm AI Hub and run them on the Hexagon NPU, Adreno GPU, or CPU compute units — all in Kotlin.
See GenieX running on Android before you write any code. The reference chat app — with model picker, resumable downloads, and VLM support — lives in qualcomm/ai-hub-apps. Clone it, open it in Android Studio, and hit Run ▶.
Pick a model from the dropdown and choose NPU, GPU, or CPU on load. Tap the image button for VLMs. Stay on Wi-Fi for the first download.
No phone? See Testing without a physical device.
minSdk = 27 (Android 8.1) in your app module.SM8750) or Snapdragon 8 Elite Gen 5 (SM8850) — see Supported platforms.```kotlin
dependencyResolutionManagement {
repositories {
google()
mavenCentral()
}
}
```
```kotlin
dependencies {
implementation("com.qualcomm.qti:geniex-android:0.3.1")
}
```
The artifact ships native `arm64-v8a` libraries — no NDK or CMake on your side.
```xml
<uses-permission android:name="android.permission.INTERNET" />
```
For VLMs that load images from the gallery, also declare `READ_EXTERNAL_STORAGE` (or scoped media permissions on Android 13+).
Next, head to the Quickstart to download and run your first model.
<Feedback/>