# Model porting best practices

## Export custom YoloV8 model using QAIRT SDK

Prerequisites

Install the Qualcomm AI Runtime SDK on a host computer with `Python >= 3.10` and `PyTorch >=1.8`.

For more details, follow [Install Qualcomm AI Runtime SDK](https://docs.qualcomm.com/doc/80-80022-15B/topic/qairt-install.html).

Run the following commands on the host computer.

1. Activate your virtual environment.

source <venv_path>/bin/activate
        Copy to clipboard
2. Install the Ultralytics package and export the ONNX model.

pip install ultralytics
        Copy to clipboard

yolo export model=yolov8s.pt imgsz=320 format=onnx opset=11 optimize=True simplify=true
        Copy to clipboard

Procedure

1. Convert the ONNX model to DLC.

snpe-onnx-to-dlc -i yolov8s.onnx
        Copy to clipboard
2. Generate quantized DLC.

    1. Prepare the calibration data set.
    2. Gather 5-10 images that used during training and save these images in the input directory.
    3. Use the `preprocess.py` script to convert `.jpg` images into the RAW files required for quantization.

Note

In this example, the model uses an input dimension of 320x320.

        1. Download the script as follows:

wget https://raw.githubusercontent.com/quic/sample-apps-for-qualcomm-linux/refs/heads/main/qualcomm-linux/scripts/preprocess.py
                Copy to clipboard
        2. Run the script with the following options:

python preprocess.py <INPUT PATH> <OUTPUT PATH> 1 0
                Copy to clipboard

            - `<INPUT PATH>`: Folder containing the original images
            - `<OUTPUT PATH>`: Folder where the RAW files will be generated
    4. Create an `input.txt` file containing the paths to all generated RAW files.

        The quantization process needs this file.
3. Quantize the model, using `snpe-dlc-quantize` to convert the model to quantized DLC.

> 
> 
> snpe-dlc-quantize --input_dlc yolov8s.dlc --input_list input.txt
>         Copy to clipboard

## Run the demo

1. Download the labels file. See [Download model files for Qualcomm Neural Processing SDK](https://docs.qualcomm.com/doc/80-80022-15B/topic/classify-objects-with-default-model.html#download-model-files).
2. On the host device, run the following command:

export USER=root
        Copy to clipboard
3. Push the test video file `/etc/media` on the device.

scp <video file> $USER@<IP address of target device>:/etc/media/
        Copy to clipboard
4. Push the quantized YoloV8 model to the device.

scp <model file> $USER@<IP address of target device>:/etc/models/
        Copy to clipboard
5. Retrieve the output tensor of the model, for example, `output0`.

![../_images/node-output0.png](data:image/png;base64,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)
6. Create a new shell.

ssh $USER@<IP address of of device>
        Copy to clipboard
7. In the new shell, run the following commands:

gst-launch-1.0 -e filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split split. ! queue ! qtivcomposer name=mixer ! queue ! waylandsink fullscreen=true sync=true split. ! queue ! qtimlvconverter ! queue ! qtimlsnpe delegate=dsp model=/etc/models/yolov8s_quantized.dlc tensors="<output0>" ! queue ! qtimlpostprocess settings="{\"confidence\": 51.0}" results=10 module=yolov8 labels=/etc/labels/yolov8.json ! video/x-raw,width=640,height=360 ! queue ! mixer.
        Copy to clipboard

Last Published: May 14, 2026

[Previous Topic
Get answers to common questions](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/troubleshooting.md) [Next Topic
Profile your AI model using Qualcomm AI Runtime SDK](https://docs.qualcomm.com/bundle/publicresource/80-80022-15B/topics/profile-your-model.md)