# Integrate a custom AI model in an application
This section describes the paths available for you to deploy your custom model with Qualcomm SDKs.
To use a custom model in an AI application, you can use the Qualcomm Intelligent Multimedia SDK or Qualcomm AI Runtime SDK.
**Bring your own model: Time taken to deploy a model**
Using Qualcomm IM SDK
| SDK supported use case? | SDK supported model? | Number of AI Hub models available | Expected time to integrate the model in an application |
| --- | --- | --- | --- |
| Yes | Yes | 16 | 15 minutes |
| Yes | No | 3 | 2 days |
| No | No | 5 | ~2 weeks
This is an advanced use case. |
Using Qualcomm AI Runtime SDK (SNPE/QNN)
| SDK supported use case? | SDK supported model? | Number of AI Hub models available | Expected time to integrate the model in an application |
| --- | --- | --- | --- |
| No constraints | No constraints | 0 | ~1 week
This is an advanced use case. |
Note
The moderate and advanced paths assume understanding of
[GStreamer fundamentals](https://gstreamer.freedesktop.org/documentation/tutorials/index.html),
understanding of [GStreamer pipelines](https://gstreamer.freedesktop.org/documentation/gstreamer/gstpipeline.html?gi-language=c),
expertise in C/C++, and a [Yocto build environment](https://docs.yoctoproject.org/2.1/yocto-project-qs/yocto-project-qs.html).
Last Published: Oct 13, 2025
[Previous Topic
Download source code for development](https://docs.qualcomm.com/bundle/publicresource/80-70018-15B/topics/download-source-code.md) [Next Topic
Integrate an AI Hub model in an application](https://docs.qualcomm.com/bundle/publicresource/80-70018-15B/topics/integrate-ai-hub-models.md)