Skip to main content

Downloading Qualcomm AI Hub Models

This guide demonstrates how to download and export a YOLO object detection model tailored specifically for the QCS6490 chipset using Qualcomm AI Hub.


Overview​

Qualcomm AI Hub is a centralized model repository and optimization service designed to streamline the deployment of AI models onto Qualcomm-powered edge devices. It provides several key advantages that simplify the AI deployment process:

  • Pre-Optimized AI Models: Access a wide library of production-ready models (such as YOLO, MobileNet, and ResNet) tuned specifically for Qualcomm architectures.
  • Hardware Acceleration (NPU/GPU/CPU): Easily compile and quantize models into formats like ONNX, TFLite, or Qualcomm AI Runtime, ensuring full utilization of on-chip AI accelerators.
  • Faster Time-to-Market: Eliminates the complexity of manual model quantization and hardware-specific kernel tuning for embedded developers.

System Requirements and Components​

ComponentSpecification
PlatformASR-D501 (Qualcomm QCS6490)
OS ImageASRD501A1-Ubuntu24.04-x07_v1.0.0
ModelYOLOv8-Detection (from Qualcomm AI Hub Models)

Workflow​

  • Step 1: Select a QCS6490-compatible model from Qualcomm AI Hub
  • Step 2: Prepare an isolated Python environment
  • Step 3: Install the model package
  • Step 4: Authenticate for Qualcomm AI Hub Workbench
  • Step 5: Export model for QCS6490

Step 1: Select a QCS6490-compatible model from Qualcomm AI Hub​

Open the Qualcomm AI Hub model catalog ↗, filter by Qualcomm Dragonwing™ QCS6490.

QAIhubmodel_chipset_choose_qcs6490

Select the model you want to run on your device. In this example, we choose YOLOv8-Detection ↗.

QAIhubmodel_yolov8-det

For export and runtime details, consult the YOLOv8-Detection source and documentation (GitHub) ↗.

Step 2: Prepare an isolated Python environment​

Confirm that your Python version is supported by the selected qai-hub-models release.
You can check the supported Python versions on the GitHub page.

yolov8-det_github


Create and activate a Python virtual environment to keep dependencies isolated from the system Python.
Replace <venv_name> with your desired environment name:

sudo apt update
sudo apt install python3-venv
python3 -m venv <venv_name>
source <venv_name>/bin/activate

Step 3: Install the model package​

Install qai-hub-models package and the YOLOv8-Detection model in your Python virtual environment:

pip install qai-hub-models==0.61.0
qai-hub-models install yolov8_det

Run the demo application with W8A8 quantization before exporting:

python3 -m qai_hub_models.models.yolov8_det.demo --quantize w8a8

The Demo Result is shown below.

yolov8_det_official_demo

A successful demo confirms that the model and its dependencies are installed correctly before exporting.

Step 4: Authenticate for Qualcomm AI Hub Workbench​

Create a Qualcomm AI Hub Workbench account ↗, and get your API token from Account → Settings → API Token.

Configure the <API_TOKEN> obtained from the Qualcomm AI Hub Workbench account:

qai-hub configure --api_token <API_TOKEN>

Note: Treat <API_TOKEN> as a secret. Do not share it publicly, post it online, or include it in any screenshots.

Step 5: Export model for QCS6490​

Before exporting the model, you can list the options supported by the model you choose with the command below:

qai-hub-models export yolov8_det --help

Export a TensorFlow Lite (TFLite) model with 8-bit weights and 8-bit activations:

qai-hub-models export yolov8_det \
--target-runtime tflite \
--quantize w8a8 \
--chipset qcs6490

In this example, the export pipeline is:

StepStageAction & FormatDescription
01Initial CompilePyTorch (.pt) → ONNXConverts the original PyTorch model into ONNX format.
02QuantizationW8A8Applies W8A8 quantization to compress the model weights and activations.
03Target CompileQuantized ONNX → TFLiteCompiles the quantized model into the target runtime (.tflite).
04ProfilingDevice BenchmarkMeasures latency and memory consumption on the physical device.
05InferenceReal-world ValidationExecutes test inference with sample inputs.


Export jobs and their individual stages can be reviewed in Qualcomm AI Hub Workbench.
Qualcomm AI Hub Workbench views used to inspect the submitted model-export jobs and stage results.

QAIhubmodel_export_pipeline

After the process is complete, the outputs will be located in the ./export_assets/yolov8_det-tflite-w8a8 folder.

Once the model export is complete, you can safely exit the virtual environment:

deactivate