# Build a customer support chatbot on Android with Llama and ExecuTorch

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/)
- [Create a development environment](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-1/)
- [Set up ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-2/)
- [Understand Llama models](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-3/)
- [Prepare Llama models for ExecuTorch](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-4/)
- [Run the chatbot on Android](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-5/)
- [Build and run the Android chat app](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/how-to-6/)
- [Next Steps](https://learn.arm.com/learning-paths/mobile-graphics-and-gaming/customer-support-chatbot-with-llama-and-executorch-on-arm-based-mobile-devices/_next-steps/)

## About this Learning Path

| Skill level:             | Introductory             |
|--------------------------|--------------------------|
| Reading time:            | 1 hr                     |
| Last updated:            | 05 Aug 2026              |

| Author:                  | Parichay Das [GitHub](https://github.com/parichaydas) [LinkedIn](https://linkedin.com/in/parichaydas) |
|--------------------------|--------------------------|
| Arm IP:                  | [Cortex-A](https://support.arm.com/?tab=compute-ip&Product%20Type=Application%20Processors) |
| Tags:                    | ML, macOS, Linux, Android, Java, Python, ExecuTorch |

### Who is this for?
This is an introductory topic for software developers interested in building an on-device customer support chatbot for Android using Meta's Llama models and the ExecuTorch runtime.

### What will you learn?
Upon completion of this Learning Path, you will be able to:
- Set up a development environment for building and deploying ExecuTorch-based apps on Android
- Describe how ExecuTorch uses KleidiAI kernels to accelerate performance on Arm-based platforms
- Export a Llama 3.2 model to `.pte` format optimized for on-device inference
- Run a Llama model on an Arm-powered Android phone and verify inference performance
- Build and run an Android chat app configured as a customer support assistant

### Prerequisites
Before starting, you will need the following:
- An Apple M1/M2/M3 development machine, or a Linux machine with at least 16GB of RAM
- An Arm-powered smartphone with the i8mm feature running Android, with 16GB of RAM
- A USB cable to connect your smartphone to your development machine
- Android Debug Bridge (adb) installed. Follow the steps in [adb](https://developer.android.com/tools/adb) to install Android SDK Platform Tools
- Java 17 JDK. Follow the steps in [Java SE 17 Archive Downloads](https://www.oracle.com/java/technologies/javase/jdk17-archive-downloads.html) to download and install JDK for your host
- Python 3.10 or later
- A [Hugging Face](https://huggingface.co/) account with access to Meta Llama models

### Summary
You’ll build and deploy an on-device Android customer support chatbot with Meta’s Llama 3.2, ExecuTorch, and KleidiAI. First, you’ll set up the environment and choose a model and quantization approach. Then, you’ll obtain Llama 3.2 1B Instruct weights and export them to `.pte`. Finally, you’ll cross-compile the runner with the Android NDK and enable KleidiAI through XNNPACK, then deploy to an Arm phone and run inference.

### Frequently asked questions

<details>
<summary>Which Llama model variant should I download, and can I use a different one?</summary>
You should use the Llama 3.2 1B Instruct model. If you want to use a different model, you can adapt the same steps to other variants with minimal modification.
</details>

<details>
<summary>What output should I have after exporting the model for ExecuTorch?</summary>
You should produce a `.pte` file. This format is optimized for on-device inference and is loadable by the ExecuTorch runtime.
</details>

<details>
<summary>What should I check if the Android cross-compile step fails to find the toolchain?</summary>
Verify that `ANDROID_NDK` is set to the correct path and that `build/cmake/android.toolchain.cmake` exists there. Also confirm your ExecuTorch dependencies are installed in the Python environment.
</details>

<details>
<summary>How do I make sure KleidiAI acceleration is included in my Android build?</summary>
Build ExecuTorch and its libraries for Android with KleidiAI kernels enabled through XNNPACK. Use the provided CMake configuration to include these kernels.
</details>

<details>
<summary>What result should I expect when I run the chatbot on the phone?</summary>
The Llama runner or chat app should load the exported model and generate responses to prompts on the device.
</details>