# Deploy LiteRT as a Native application

You can run LiteRT models using a sample LiteRT application called
`label_image`, which is a part of the TensorFlow repository. The
`label_image` sample application and the LiteRT library are cross-compiled
and installed on the target device.

The `label_image` sample application does the following:

1. Loads a classification LiteRT model.
2. Performs inference on an image using a delegate to speed up the model
on the Qualcomm hardware.
3. Runs inference using either of the following delegates.

    To run the model on the Arm^®^ CPU using the XNNPACK delegate:

label_image -l /etc/artifacts/labels.txt \
                    -i /etc/artifacts/grace_hopper.bmp \
                    -m /etc/artifacts/mobilenet_v1_1.0_224_quant.tflite \
                    -c 10 \
                    -p 1 \
                    --xnnpack_delegate 1
        Copy to clipboard

    To run the model on the Adreno GPU using the GPU delegate:

label_image -l /etc/artifacts/labels.txt \
                    -i /etc/artifacts/grace_hopper.bmp \
                    -m /etc/artifacts/mobilenet_v1_1.0_224.tflite \
                    -c 10 \
                    -p 1 \
                    --gl_backend 1
        Copy to clipboard

Last Published: May 14, 2026

[Previous Topic
Deploy a LiteRT model](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/deploy-a-litert-model.md) [Next Topic
Deploy LiteRT with an IMSDK application](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/deploy-litert-with-an-imsdk-application.md)