# AI developer workflow documentation Run prebuilt models and AI applications, compile and optimize AI models, and develop your own AI application. ## Overview Overview https://docs.qualcomm.com/doc/80-80022-15B/topic/ai-ml-developer-workflow.html ## Run prebuilt AI models and applications Use sample applications to run AI/ML models or customize the sample app. Run a LiteRT model on NPU Run a LiteRT model using the Qualcomm AI Runtime delegate with Python. https://docs.qualcomm.com/doc/80-80022-15B/topic/run-a-litert-model-using-delegate.html Experience AI applications with Qdemo UI Experience Qualcomm AI features with a simple to use GUI demonstration. https://docs.qualcomm.com/doc/80-80022-15B/topic/run-the-gui-demo.html Run a sample application using EVK Classify images with the IM SDK sample application and an EVK. https://docs.qualcomm.com/doc/80-80022-15B/topic/sample-app-evk.html Run a sample application using QDC Classify images with the default sample application and Qualcomm Device Cloud (QDC). https://docs.qualcomm.com/doc/80-80022-15B/topic/sample-app-qdc.html ## Compile and optimize an AI model Download preoptimized models or convert, quantize, and fine tune accuracy for your own model. Use AI Hub to optimize an AI model Use AI Hub to download a preoptimized model or optimize your own model. https://docs.qualcomm.com/doc/80-80022-15B/topic/ai-hub.html Use Qualcomm AI Runtime SDK to optimize an AI model Port your models using the Qualcomm AI Runtime (QAIRT) SDK. https://docs.qualcomm.com/doc/80-80022-15B/topic/qairt.html Fine tune an AI model with custom data using Edge Impulse Fine tune models using your own data and Edge Impulse. https://docs.qualcomm.com/doc/80-80022-15B/topic/edge-impulse.html Fine tune model accuracy using Qualcomm AI Model Efficiency Toolkit Fine tune model accuracy using the Qualcomm AI Model Efficiency Toolkit. https://docs.qualcomm.com/doc/80-80022-15B/topic/aimet.html ## Run inference with and benchmark available frameworks and runtimes Use ONNX and LiteRT models with available back-ends for inference and benchmarking. Run LiteRT models using delegates and back-ends Run a LiteRT model using the available delegates and back-ends. https://docs.qualcomm.com/doc/80-80022-15B/topic/litert-overview.html Run an ONNX model on NPU using ORT Run an ONNX model on the neural processing unit (NPU) using the ONNXX runtime (ORT). https://docs.qualcomm.com/doc/80-80022-15B/topic/run-an-onnx-model-using-ort.html ## Develop your own AI/ML application Implement your own application on a Qualcomm platform. This is an advanced topic and is for experienced developers. Develop your own AI/ML application with the Qualcomm Visual Studio Code Extension Build an AI/ML application using the Qualcomm Visual Studio Code Extension. https://docs.qualcomm.com/doc/80-80022-15B/topic/develop-your-own-application-ide.html Develop an AI/ML application using Qualcomm Intelligent Multimedia SDK Build an AI/ML application using GStreamer and the Qualcomm IM SDK. https://docs.qualcomm.com/doc/80-80022-15B/topic/develop-your-own-application-im-sdk.html Develop an AI/ML application using Qualcomm AI Runtime SDK C++ APIs Build an AI/ML application using C++ and the QAIRT SDK. https://docs.qualcomm.com/doc/80-80022-15B/topic/develop-your-own-application-qairt-cpp.html ## Use AI Hub models with the GStreamer API Run AI Hub models and labels with GStreamer commands on Qualcomm evaluation kits. Classify images Classify images from the Imagenet dataset. https://docs.qualcomm.com/doc/80-80022-15B/topic/image-classification.html Detect objects Predict bounding boxes and classes of objects in an image. https://docs.qualcomm.com/doc/80-80022-15B/topic/object-detection.html Apply semantic segmentation to frames of a video Assign a class label to every pixel in an image. https://docs.qualcomm.com/doc/80-80022-15B/topic/semantic-segmentation.html Upscale images with super resolution Upscale images on to sharpen them in real-time. https://docs.qualcomm.com/doc/80-80022-15B/topic/super-resolution.html ## Run on-device generative AI (GenAI) Run GenAI models on Qualcomm evaluation kits. Prepare a GenAI model Prepare a GenAI model for execution on Qualcomm® Dragonwing™ IoT devices. https://docs.qualcomm.com/doc/80-80022-15B/topic/prepare-genai-model.html Run a GenAI model Run a prepared GenAI model on a Qualcomm Dragonwing IoT device. https://docs.qualcomm.com/doc/80-80022-15B/topic/run-genai-model.html Use GenAI models with Qualcomm Generative AI Inference Extensions (Genie) Prepare, manage, and execute GenAI models with Genie. https://docs.qualcomm.com/doc/80-80022-15B/topic/use-genai-model-with-genie.html Develop a GenAI application Build your own GenAI application based on a Qualcomm sample application. https://docs.qualcomm.com/doc/80-80022-15B/topic/develop-genai-app.html ## Troubleshooting and FAQ Get answers to common questions Get answers to common questions and learn how to get additional help. https://docs.qualcomm.com/doc/80-80022-15B/topic/troubleshooting.html Export YoloV8 model using Qualcomm Neural Processing Engine Follow model porting best practices to export the YoloV8 model using SNPE. https://docs.qualcomm.com/doc/80-80022-15B/topic/appx-export-yolov8.html Profile your AI model Profile your AI model to optimize performance and resource utilization. https://docs.qualcomm.com/doc/80-80022-15B/topic/profile-your-model.html Last Published: May 14, 2026 [Next Topic Overview](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/ai-ml-developer-workflow.md)