# AI Hub – Qualcomm IM SDK

Source: [https://docs.qualcomm.com/doc/80-70015-15B/topic/ai-hub-imsdk.html](https://docs.qualcomm.com/doc/80-70015-15B/topic/ai-hub-imsdk.html)

This section explains how to use AI Hub models and labels with gstreamer commands on
        Qualcomm Linux Development Kits.

## Prerequisites

1. Download model files from [IoT - Qualcomm AI Hub](https://aihub.qualcomm.com/iot/models)
2. Filter by **Chipset** and select **QualcommQCS6490** for RB3Gen2 and
                         **QualcommQCS8550** for QCS9075.
3. Download the label files from [ai-hub-models/qai_hub_models/labels at main ·
                        quic/ai-hub-models (github.com)](https://github.com/quic/ai-hub-models/tree/main/qai_hub_models/labels)
                    
Note: To enable performance mode, update the HTP external
                        delegate parameter in the gst-launch-1.0 command as given
                        below:

        external-delegate-options="QNNExternalDelegate,backend_type=htp,htp_device_id=(string)0,htp_performance_mode=(string)2,htp_precision=(string)1;"Copy to clipboard
4. Push the model and label to the /opt/ directory on the target device .

Last Published: Jan 21, 2026

[Previous Topic
Steps to update BitBake files for plugin compilation](https://docs.qualcomm.com/bundle/publicresource/80-70015-15B/topics/steps-to-update-bitbake-for-compilation.md) [Next Topic
Image classification](https://docs.qualcomm.com/bundle/publicresource/80-70015-15B/topics/image-classification.md)