Hugging Face's logo

qualcomm
/
Yolo-X

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community

Yolo-X: Optimized for Qualcomm Devices

YoloX is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-X found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8_mixed_int16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Yolo-X on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Yolo-X on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Model checkpoint: YoloX Small
  • Input resolution: 640x640
  • Number of parameters: 8.98M
  • Model size (float): 34.3 MB
  • Model size (w8a16): 9.53 MB
  • Model size (w8a8): 8.96 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Yolo-X ONNX float Snapdragon® X2 Elite 7.654 ms 208 - 208 MB NPU
Yolo-X ONNX float Snapdragon® X Elite 13.613 ms 151 - 151 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 9.235 ms 5 - 177 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 1 Mobile 25.937 ms 5 - 203 MB NPU
Yolo-X ONNX float Qualcomm® QCS8550 (Proxy) 14.096 ms 0 - 21 MB NPU
Yolo-X ONNX float Qualcomm® QCS8450 25.937 ms 5 - 203 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Mobile 7.747 ms 2 - 160 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Gen 5 Mobile 6.209 ms 3 - 160 MB NPU
Yolo-X ONNX float Qualcomm® QCS9075 16.62 ms 5 - 50 MB NPU
Yolo-X ONNX float Qualcomm® QCS8750 7.747 ms 2 - 160 MB NPU
Yolo-X ONNX float Qualcomm® QCS7181 13.613 ms 151 - 151 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 11.385 ms 210 - 210 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.975 ms 179 - 179 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 10.073 ms 0 - 225 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 16.3 ms 0 - 227 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS6490 25.919 ms 2 - 48 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS8550 (Proxy) 14.188 ms 2 - 25 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS8450 16.3 ms 0 - 227 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 11.064 ms 1 - 203 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Mobile 8.86 ms 0 - 206 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS9075 14.578 ms 2 - 48 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.627 ms 3 - 203 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCM6690 66.309 ms 3 - 204 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS7790 10.627 ms 3 - 203 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS8750 8.86 ms 0 - 206 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS7181 14.975 ms 179 - 179 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.185 ms 180 - 180 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 8.939 ms 148 - 148 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.145 ms 1 - 83 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 8.756 ms 0 - 81 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS6490 12.271 ms 1 - 46 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS8550 (Proxy) 8.334 ms 0 - 13 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS8450 8.756 ms 0 - 81 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS9075 9.282 ms 1 - 46 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCM6690 30.081 ms 1 - 173 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 8.895 ms 1 - 172 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.087 ms 1 - 57 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Mobile 5.778 ms 1 - 58 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS7790 8.895 ms 1 - 172 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS8750 5.778 ms 1 - 58 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS7181 8.939 ms 148 - 148 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 27.558 ms 176 - 176 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 34.489 ms 147 - 147 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 26.032 ms 10 - 849 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS8550 (Proxy) 33.735 ms 0 - 24 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Mobile 22.777 ms 12 - 803 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 25.215 ms 10 - 801 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS9075 38.897 ms 9 - 53 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS8750 22.777 ms 12 - 803 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® QCS7181 34.489 ms 147 - 147 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.6 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 6.073 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.63 ms 2 - 105 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 7.01 ms 2 - 107 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS6490 17.09 ms 2 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8275 11.688 ms 1 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 5.526 ms 2 - 4 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 7.01 ms 2 - 107 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.941 ms 2 - 83 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.6 ms 0 - 79 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS9075 6.035 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 6.921 ms 1 - 189 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCM6690 45.877 ms 3 - 195 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 7.576 ms 0 - 69 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA7255P 11.688 ms 1 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS7790 6.921 ms 1 - 189 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8750 2.6 ms 0 - 79 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS7181 6.073 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X2 Elite 1.375 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X Elite 2.746 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.651 ms 1 - 78 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.978 ms 1 - 77 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS6490 7.556 ms 3 - 6 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8275 5.855 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 2.47 ms 1 - 29 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8450 2.978 ms 1 - 77 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS9075 3.298 ms 3 - 5 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA7255P 5.855 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCM6690 24.802 ms 1 - 167 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.781 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8295P 3.784 ms 1 - 48 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.904 ms 1 - 54 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 1.171 ms 0 - 46 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS7790 2.781 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8750 1.171 ms 0 - 46 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS7181 2.746 ms 1 - 1 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.651 ms 0 - 71 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.94 ms 0 - 77 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS6490 7.024 ms 0 - 12 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8275 5.872 ms 0 - 46 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 2.474 ms 0 - 23 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8775P 45.297 ms 8 - 41 MB GPU
Yolo-X TFLITE w8a8 Qualcomm® SA8650P 45.297 ms 8 - 41 MB GPU
Yolo-X TFLITE w8a8 Qualcomm® SA8255P 45.297 ms 8 - 41 MB GPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8450 2.94 ms 0 - 77 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS9075 3.349 ms 0 - 12 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA7255P 5.872 ms 0 - 46 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCM6690 22.912 ms 0 - 158 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.768 ms 0 - 46 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8295P 3.793 ms 0 - 45 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.918 ms 0 - 49 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite Mobile 1.195 ms 0 - 45 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS7790 2.768 ms 0 - 46 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8750 1.195 ms 0 - 45 MB NPU

License

  • The license for the original implementation of Yolo-X can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support