# Setup AI Runtime

This tutorial requires the following setup which takes about 20-30 minutes to complete. For more information about the setup, see [qnn_setup.ps1](https://raw.githubusercontent.com/quic/wos-ai/refs/heads/main/Scripts/qnn_setup.ps1).

1. Open PowerShell in administrator mode and run the following commands to install the dependencies. You must run PowerShell in administrator mode to grant the elevated permissions required to automatically install the necessary applications and execute the PowerShell scripts.
2. Set `$DIR_PATH`. By default it is set to `C:\\WoS_AI` although you can change to your desired path.

$DIR_PATH  = "C:\WoS_AI"
        Copy to clipboard
3. Run the following command to download the setup script.

if (!(Test-Path $DIR_PATH\Downloads\Setup_Scripts)) {mkdir $DIR_PATH\Downloads\Setup_Scripts}
        Invoke-WebRequest -O qnn_setup.ps1 https://raw.githubusercontent.com/quic/wos-ai/refs/heads/main/Scripts/qnn_setup.ps1
        Move-Item -Path ".\qnn_setup.ps1" -Destination $DIR_PATH\Downloads\Setup_Scripts -Force
        Copy to clipboard
4. If running scripts is disabled on the system, run the following command and enter ‘A’(Yes for all).

Set-ExecutionPolicy RemoteSigned
        Copy to clipboard
5. Run the following command to install the prerequisites for AI Runtime (QNN).

    QNN-Setup:

cd $DIR_PATH
        Copy to clipboard

powershell  -command "&{. .\Downloads\Setup_Scripts\qnn_setup.ps1; QNN_Setup -rootDirPath $DIR_PATH}"
        Copy to clipboard

    The command downloads and installs the following dependencies:

> 
> 
> - Python amd64 version 3.10.4
>     - Model artifacts include mobilenet\_v2.onnx model and io\_utils.py for pre/post processing.
>     - AI Runtime SDK version 2.42.0.251225
>     - Visual Studio Enterprise version 17.10.3
>     - CMake version 3.30.4
>     - Creates a virtual environment (QAIRT\_VENV) with the necessary libraries for the AI Runtime (QNN).
6. When setup is complete, the following folder structure is in $DIR\_PATH:

![../../_images/folders_structure_qnn.png](data:image/png;base64,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)
    - Downloads: This folder stores all the files required to complete the setup, such as Python installers and setup scripts.
    - Python\_Env: This directory has the virtual environment (QAIRT\_VENV) created for the EPs.
    - Debug\_Logs: This directory has logs corresponding to setup.
    - Models: This directory holds model sub-directories and its respective artifacts(Ex: Mobilenet\_v2) along with QNN dependencies like libraries and skel files(Ex: QNN\_Dependencies).

## Next steps

After completing setup, continue to the [Model Conversion](https://docs.qualcomm.com/doc/80-62010-1/topic/model-convert-quantize.html#model-convert-quantize) step using AI Runtime tools in the next section.

Last Published: Jun 16, 2026

[Previous Topic
QNN Workflow](https://docs.qualcomm.com/bundle/publicresource/80-62010-1/topics/qnn-workflow.md) [Next Topic
Model Conversion](https://docs.qualcomm.com/bundle/publicresource/80-62010-1/topics/model-convert-quantize.md)