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 7.598 ms 5 - 5 MB NPU
Yolo-X ONNX float Snapdragon® X Elite 13.455 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 9.255 ms 5 - 186 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 1 Mobile 25.599 ms 1 - 208 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.851 ms 5 - 151 MB NPU
Yolo-X ONNX float Qualcomm® QCS8450 25.599 ms 1 - 208 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Gen 5 Mobile 6.288 ms 5 - 164 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite Mobile 7.742 ms 3 - 162 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ IQ-9075 16.563 ms 5 - 7 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ Q-8750 7.742 ms 3 - 162 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ IQ-X7181 13.455 ms 14 - 14 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 11.439 ms 2 - 2 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.992 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 10.188 ms 3 - 239 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 15.887 ms 3 - 242 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 29.87 ms 2 - 5 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 14.142 ms 0 - 10 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS8450 15.887 ms 3 - 242 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Mobile 8.855 ms 1 - 206 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 14.573 ms 2 - 5 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.598 ms 3 - 202 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 11.05 ms 1 - 209 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 63.165 ms 3 - 208 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 10.598 ms 3 - 202 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 8.855 ms 1 - 206 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 14.992 ms 7 - 7 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.185 ms 180 - 180 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 8.979 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.195 ms 1 - 90 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 8.809 ms 1 - 92 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 13.562 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.306 ms 0 - 11 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS8450 8.809 ms 1 - 92 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Mobile 5.8 ms 1 - 62 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 8.931 ms 1 - 176 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 8.5 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 8.098 ms 0 - 60 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 29.604 ms 1 - 178 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 8.931 ms 1 - 176 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 5.8 ms 1 - 62 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 8.979 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 27.422 ms 16 - 16 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 34.082 ms 18 - 18 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 25.974 ms 11 - 860 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.697 ms 9 - 14 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Mobile 23.059 ms 12 - 814 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 35.931 ms 13 - 15 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 25.273 ms 13 - 807 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ Q-8750 23.059 ms 12 - 814 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 34.082 ms 18 - 18 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.614 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 6.081 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.633 ms 0 - 104 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 7.115 ms 2 - 107 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 23.108 ms 3 - 7 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8275 11.673 ms 0 - 71 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.528 ms 2 - 4 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8775P 6.148 ms 0 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8650P 6.148 ms 0 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8255P 6.148 ms 0 - 72 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 7.115 ms 2 - 107 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.609 ms 2 - 81 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.847 ms 2 - 6 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA7255P 11.673 ms 0 - 71 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 7.6 ms 0 - 69 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 6.894 ms 2 - 189 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.963 ms 2 - 85 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 45.077 ms 3 - 196 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 6.894 ms 2 - 189 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.609 ms 2 - 81 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.081 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X2 Elite 1.235 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X Elite 2.742 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.647 ms 1 - 73 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.984 ms 1 - 76 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 8.678 ms 1 - 4 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8275 5.872 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.442 ms 1 - 3 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8775P 2.821 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8650P 2.821 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8255P 2.821 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8450 2.984 ms 1 - 76 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 1.171 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.784 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 2.955 ms 0 - 3 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA7255P 5.872 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8295P 3.796 ms 1 - 48 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.91 ms 1 - 53 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 22.518 ms 2 - 162 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.784 ms 1 - 49 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 1.171 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 2.742 ms 1 - 1 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.646 ms 0 - 78 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.962 ms 0 - 74 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 8.733 ms 0 - 12 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8275 5.875 ms 0 - 47 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.438 ms 0 - 3 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8775P 2.933 ms 0 - 51 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8650P 2.933 ms 0 - 51 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8255P 2.933 ms 0 - 51 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8450 2.962 ms 0 - 74 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite Mobile 1.2 ms 0 - 50 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.77 ms 0 - 45 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 2.634 ms 0 - 12 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA7255P 5.875 ms 0 - 47 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8295P 3.806 ms 0 - 45 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.921 ms 0 - 51 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 21.555 ms 0 - 158 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 2.77 ms 0 - 45 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 1.2 ms 0 - 50 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