# Overview

Source: [https://docs.qualcomm.com/doc/80-70017-54/topic/tflite-landing-page.html](https://docs.qualcomm.com/doc/80-70017-54/topic/tflite-landing-page.html)

Lite Runtime (LiteRT) is an open-source deep learning framework designed for on-device
            inference. The TensorFlow framework provides tools and APIs to convert a standard
            pretrained TensorFlow model from the SavedModel or Keras format into a LiteRT
            format.

This guide describes the available delegates and methods to execute LiteRT models using
            the Qualcomm^®^ software stack, and explains how to:

- Run LiteRT models using the Gstreamer-based Qualcomm^®^ Intelligent
                Multimedia SDK (IM SDK) or the native LiteRT application.
- Convert TensorFlow models to LiteRT models and optimize them for on-device
                inference.
- Execute LiteRT models using a delegate on hardware accelerators, such as CPU, GPU,
                and the Qualcomm^®^ Hexagon™ Tensor Processor.
- Benchmark LiteRT models.

Run a LiteRT model

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-1 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Use the Gstreamer-based IM SDK](https://docs.qualcomm.com/doc/80-70017-54/topic/getting-started.html#run-a-tensorflow-lite-model-using-the-gstreamer-based-qim-sdk)

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-4 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Use a native LiteRT sample application](https://docs.qualcomm.com/doc/80-70017-54/topic/getting-started.html#run-a-tensorflow-lite-model-using-a-native-tensorflow-lite-sample-application)

LiteRT developer workflow

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-2 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Convert a TensorFlow
                                model to a LiteRT model](https://docs.qualcomm.com/doc/80-70017-54/topic/tensorflow-lite-developer-workflow.html#convert-tensorflow-lite-models)

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-5 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Create an application and run
                                inference](https://docs.qualcomm.com/doc/80-70017-54/topic/tensorflow-lite-developer-workflow.html#run-inference)

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-7 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Develop a custom application](https://docs.qualcomm.com/doc/80-70017-54/topic/tensorflow-lite-developer-workflow.html#develop-a-custom-application-to-run-the-tensorflow-lite-model)

Sample applications

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-3 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Download models and
                                sample images](https://docs.qualcomm.com/doc/80-70017-54/topic/sample-applications.html#download-models-and-sample-images)

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-6 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Run a LiteRT model using an available
                                delegate](https://docs.qualcomm.com/doc/80-70017-54/topic/sample-applications.html#label-image-tool)

<?xml version="1.0" encoding="UTF-8"?>

<svg id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" width="21" height="18" viewbox="0 0 21 18">
  <defs>
    <style>.svg-8 .cls-1 { fill: none; stroke: #3253dc; stroke-linecap: round; stroke-linejoin: round; stroke-width: 1.5px }</style>
  </defs>
  <path class="cls-1" d="M4.7,9.4h11.7M16.4,9.4l-5.8-5.8M16.4,9.4l-5.8,5.8"></path>
</svg>

                            [Run a QNN delegate using an external delegate](https://docs.qualcomm.com/doc/80-70017-54/topic/sample-applications.html#run-qnn-delegate-using-the-external-delegate-interface)

Note: See [Hardware SoCs](https://docs.qualcomm.com/bundle/publicresource/topics/80-70017-115/soc.html) that are supported on
                Qualcomm^®^ Linux^®^.

Last Published: Jan 06, 2025

[Next Topic
Get started](https://docs.qualcomm.com/bundle/publicresource/80-70017-54/topics/getting-started.md)