Back to All
Developer Blog

Build Qt Edge AI applications faster on Dragonwing IQ‑9075 with Qt Onboard

Co-written with Samuli Piippo, Ari Parkkila and Alex Bu (Qt Group).

Welcome to Part 4 of our FactoryPulse series. In our previous post, we demonstrated on-device LLMs with RAG and ASR running concurrently on the Qualcomm Dragonwing™ IQ-9075 EVK, powered by Qualcomm® Hexagon™ HTP accelerators.

In this article, we introduce Qt Onboard, an embedded Linux platform with integrated Qt tooling built on the vendor-supplied Yocto distribution.

Developed by Qualcomm Technologies and The Qt Group, Qt Onboard simplifies embedded Linux deployment and accelerates Qt-based Edge AI development on Dragonwing IoT platforms. It is delivered as a Qt Board Support Package (QBSP), including a ready-to-use image and preconfigured toolchain.

Sign up for Developer monthly newsletter

Join thousands of developers around the globe who receive latest news and updates from our monthly curated newsletter.

Qt Online Installer with the Dragonwing IQ-9075 EVK package selected under Extended Evaluation. Developers can install the QBSP from the same tool they already use for Qt.
Figure 1. Qt Online Installer with the Dragonwing IQ-9075 EVK package selected under Extended Evaluation. Developers can install the QBSP from the same tool they already use for Qt.

Why Qt Onboard was created

The primary goal of the project was to identify and remove pain points for Qt developers building Edge AI applications on Dragonwing IoT products. The full developer experience was analyzed across all stages of development: 

  • Development environment setup (Yocto) 
  • User experience / user interface (UX/UI) design (Figma) 
  • Software development 
  • AI model training 
  • Cross-compilation 
  • Deployment 
  • Execution on target hardware 

 

The Yocto challenge

Yocto is powerful but complex. Developers typically need to: 

  • Build their own Yocto-based toolchain 
  • Create a board image 
  • Configure and test the environment 

Learning Yocto can take years, and configuring and building a proper setup can take hours or days. The clear objective was to eliminate this complexity and enable developers to set up their environment in minutes. 

* Skip Yocto complexity and start in minutes

Get a pre-configured Qt + Dragonwing IQ-9075 EVK environment ready out of the box.

Request your evaluation license and install Qt Onboard.

 

Boot to Qt as the foundation

Qt Group already had a solution: Boot to Qt - a Qt-optimized platform for embedded Linux systems. It provides Qt Board Support Packages (QBSPs) that include: 

  • A ready-to-use image 
  • A pre-configured toolchain 
  • Integration with the Qt Creator IDE 

Introducing Qt Onboard

To achieve full compatibility with Qualcomm® Linux® software stack, the team chose to build the new QBSP packages on top of the official Qualcomm Linux instead of adding Qualcomm board support to Boot to Qt. Existing integrations with Qt tooling, such as the Qt Creator IDE, were migrated from Boot to Qt to this new embedded Linux platform, resulting in a solution called Qt Onboard.

Supported Boards

As of now, Qt Onboard QBSPs are available for the Dragonwing IQ-9075 EVK. QBSPs for additional  Dragonwing IoT boards will be released as they become publicly available. 

Each QBSP includes: 

  • The Qualcomm Linux  
  • Qt runtime (version 6.11) 
  • SDK for cross-compilation 
  • Deployment and execution support via the Qt Creator IDE 

This reduces environment setup time from days to minutes. Developers no longer need to build their own Yocto-based BSP or configure the entire toolchain manually — the pre-integrated and tested QBSP dramatically reduces the effort required to get started.

Availability

The Qt Onboard QBSP is available for Qualcomm® IoT boards through the standard Qt Online Installer. To try it: 

  • Install the QBSP through the Qt Online Installer (see Figure 1). 

Customizations for FactoryPulse

The Qt Onboard image built for the Dragonwing IQ-9075 EVK was customized to run the FactoryPulse solution. The following adjustments were made: 

  • Replaced PulseAudio with ALSA in Qt Multimedia to support the USB audio driver 
  • Added a GStreamer plug-in to support QML integration 
  • Added the Genie library to run the LLM 
  • Added the ONNX Runtime to test text-to-speech (TTS) — not used in the final demonstration 
  • Added a new driver for a customized USB camera, per Edge Impulse's request 

All customizations are specific to this hardware configuration and the FactoryPulse implementation.

Developer impact

Qt Onboard enables: 

  • Faster embedded Linux bring-up 
  • Reduced Yocto complexity 
  • Seamless Qt Creator IDE integration 
  • Faster iteration cycles for Edge AI development 

By combining Qualcomm Linux with Qt tooling, Qt Onboard provides a streamlined path from development to deployment on Qualcomm IoT platforms. 

Next steps

To start building with Qt Onboard: 

  • Download the QBSP for Dragonwing IQ-9075 EVK through the Qt Online Installer. 
  • Set up the environment in minutes. 
  • Deploy and run Qt applications on target hardware. 

Go from setup to deployment in minutes

Build and run Qt Edge AI applications On Dragonwing IQ-9075 EVK (link) without Yocto overhead.

Download Qt Onboard and start building with a free 90 days evaluation license (link)

Join Developer Discord

Come for support, stay for the community

Get support from experts, connect with like-minded developers, and access exclusive virtual events.

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.

About the Author
Tommi Mänttäri
Tommi Mänttäri

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patents are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.