# Use AI Hub models and labels with the GStreamer API

This section explains how to use AI Hub models and labels with
GStreamer commands on Qualcomm evaluation kits.

Prerequisites

1. Download model files from [IoT - Qualcomm AI Hub](https://aihub.qualcomm.com/iot/models)
2. Filter by **Chipset** and select **Qualcomm QCS6490** for RB3 Gen 2, **Qualcomm QCS9075** for QCS9075 and **Qualcomm QCS8275** for QCS8275.
3. If you haven’t downloaded the label files from any of previous sections, download and unzip the labels by running the following commands on your device:

wget https://github.com/quic/sample-apps-for-qualcomm-linux/releases/download/GA1.4-rel/labels.zip
        unzip -d /etc/ labels.zip
        Copy to clipboard
4. Push the models to the `/etc/` directory on the target device .

    - `/etc/models/` for all model files
    - `/etc/labels/` for all label files
    - `/etc/media/` for all video files
    - `/etc/configs/` for all configuration files

Note

The constants for each model may change
subject to AI Hub models being updated.

See [Integrate an AI Hub model in an application](https://docs.qualcomm.com/doc/80-70018-15B/topic/integrate-ai-hub-models.html) for model constant information.

Last Published: Oct 13, 2025

[Previous Topic
Develop a superresolution plugin](https://docs.qualcomm.com/bundle/publicresource/80-70018-15B/topics/development-process-for-new-plugin.md) [Next Topic
Classify images](https://docs.qualcomm.com/bundle/publicresource/80-70018-15B/topics/image-classification.md)