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 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8_mixed_int16 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a16 Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Yolo-X ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 6.335 ms 0 - 159 MB NPU
Yolo-X ONNX float Snapdragon® 8 Elite For Galaxy Mobile 7.58 ms 0 - 154 MB NPU
Yolo-X ONNX float Snapdragon® X2 Elite 7.722 ms 5 - 5 MB NPU
Yolo-X ONNX float Snapdragon® X Elite 13.643 ms 14 - 14 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 3 Mobile 9.082 ms 2 - 177 MB NPU
Yolo-X ONNX float Snapdragon® 8 Gen 1 Mobile 21.442 ms 1 - 203 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ IQ-8275 15.249 ms 5 - 9 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.431 ms 0 - 17 MB NPU
Yolo-X ONNX float Qualcomm® QCS8450 21.442 ms 1 - 203 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ IQ-9075 16.782 ms 5 - 8 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ IQ-X7181 13.643 ms 14 - 14 MB NPU
Yolo-X ONNX float Qualcomm® Dragonwing™ Q-8750 7.58 ms 0 - 154 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 10.792 ms 1 - 203 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 8.721 ms 0 - 197 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X2 Elite 11.118 ms 2 - 2 MB NPU
Yolo-X ONNX w8a16 Snapdragon® X Elite 14.517 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 9.916 ms 3 - 232 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 15.293 ms 3 - 234 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 24.85 ms 2 - 6 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 13.702 ms 2 - 6 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.659 ms 0 - 10 MB NPU
Yolo-X ONNX w8a16 Qualcomm® QCS8450 15.293 ms 3 - 234 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 14.664 ms 2 - 6 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 14.517 ms 7 - 7 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 61.659 ms 3 - 202 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 10.072 ms 3 - 194 MB NPU
Yolo-X ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 8.721 ms 0 - 197 MB NPU
Yolo-X ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.072 ms 3 - 194 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 8.069 ms 0 - 59 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.772 ms 1 - 65 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X2 Elite 8.151 ms 1 - 1 MB NPU
Yolo-X ONNX w8a8 Snapdragon® X Elite 8.824 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 6.146 ms 1 - 91 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 8.56 ms 1 - 95 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 12.16 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 8.216 ms 1 - 5 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.263 ms 0 - 12 MB NPU
Yolo-X ONNX w8a8 Qualcomm® QCS8450 8.56 ms 1 - 95 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 8.421 ms 1 - 4 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 8.824 ms 8 - 8 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 27.912 ms 1 - 174 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 8.863 ms 1 - 169 MB NPU
Yolo-X ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 5.772 ms 1 - 65 MB NPU
Yolo-X ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 8.863 ms 1 - 169 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 22.573 ms 6 - 661 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Elite For Galaxy Mobile 20.118 ms 6 - 643 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X2 Elite 23.78 ms 7 - 7 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® X Elite 29.36 ms 18 - 18 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Snapdragon® 8 Gen 3 Mobile 21.754 ms 6 - 681 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-8275 28.479 ms 6 - 9 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 28.899 ms 6 - 353 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-9075 30.271 ms 6 - 8 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ IQ-X7181 29.36 ms 18 - 18 MB NPU
Yolo-X ONNX w8a8_mixed_int16 Qualcomm® Dragonwing™ Q-8750 20.118 ms 6 - 643 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.242 ms 3 - 156 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 3.789 ms 0 - 153 MB NPU
Yolo-X QNN_DLC float Snapdragon® X2 Elite 4.104 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® X Elite 7.322 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Gen 3 Mobile 4.855 ms 5 - 178 MB NPU
Yolo-X QNN_DLC float Snapdragon® 8 Gen 1 Mobile 14.175 ms 5 - 203 MB NPU
Yolo-X QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 9.74 ms 5 - 12 MB NPU
Yolo-X QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.756 ms 5 - 7 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8775P 9.442 ms 0 - 151 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8650P 9.442 ms 0 - 151 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8255P 9.442 ms 0 - 151 MB NPU
Yolo-X QNN_DLC float Qualcomm® QCS8450 14.175 ms 5 - 203 MB NPU
Yolo-X QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 9.185 ms 7 - 14 MB NPU
Yolo-X QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 7.322 ms 5 - 5 MB NPU
Yolo-X QNN_DLC float Qualcomm® Dragonwing™ Q-8750 3.789 ms 0 - 153 MB NPU
Yolo-X QNN_DLC float Qualcomm® SA8295P 13.254 ms 2 - 172 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.943 ms 2 - 82 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.477 ms 2 - 78 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X2 Elite 2.552 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® X Elite 5.963 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.568 ms 2 - 108 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 7.036 ms 2 - 109 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 17.449 ms 0 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 5.095 ms 2 - 8 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.436 ms 2 - 4 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8650P 6.171 ms 0 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8255P 6.171 ms 0 - 73 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® QCS8450 7.036 ms 2 - 109 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.692 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.963 ms 2 - 2 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 46.882 ms 2 - 190 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 6.549 ms 2 - 184 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.477 ms 2 - 78 MB NPU
Yolo-X QNN_DLC w8a16 Qualcomm® SA8295P 7.323 ms 0 - 71 MB NPU
Yolo-X QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 6.549 ms 2 - 184 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.91 ms 1 - 51 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.16 ms 0 - 51 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X2 Elite 1.292 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® X Elite 2.702 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.593 ms 1 - 74 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 2.88 ms 1 - 79 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 7.087 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 2.319 ms 1 - 5 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.385 ms 1 - 3 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8775P 2.759 ms 1 - 55 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8650P 2.759 ms 1 - 55 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8255P 2.759 ms 1 - 55 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® QCS8450 2.88 ms 1 - 79 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 2.502 ms 3 - 6 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 2.702 ms 1 - 1 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 20.466 ms 1 - 163 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.719 ms 1 - 52 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 1.16 ms 0 - 51 MB NPU
Yolo-X QNN_DLC w8a8 Qualcomm® SA8295P 3.546 ms 1 - 50 MB NPU
Yolo-X QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.719 ms 1 - 52 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 3.224 ms 0 - 168 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 3.797 ms 0 - 166 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Gen 3 Mobile 4.87 ms 0 - 186 MB NPU
Yolo-X TFLITE float Snapdragon® 8 Gen 1 Mobile 14.175 ms 0 - 215 MB NPU
Yolo-X TFLITE float Qualcomm® Dragonwing™ IQ-8275 9.717 ms 0 - 27 MB NPU
Yolo-X TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.871 ms 0 - 3 MB NPU
Yolo-X TFLITE float Qualcomm® SA8775P 42.137 ms 3 - 34 MB GPU
Yolo-X TFLITE float Qualcomm® SA8650P 42.137 ms 3 - 34 MB GPU
Yolo-X TFLITE float Qualcomm® SA8255P 42.137 ms 3 - 34 MB GPU
Yolo-X TFLITE float Qualcomm® QCS8450 14.175 ms 0 - 215 MB NPU
Yolo-X TFLITE float Qualcomm® Dragonwing™ IQ-9075 9.252 ms 0 - 26 MB NPU
Yolo-X TFLITE float Qualcomm® Dragonwing™ Q-8750 3.797 ms 0 - 166 MB NPU
Yolo-X TFLITE float Qualcomm® SA7255P 101.323 ms 3 - 30 MB GPU
Yolo-X TFLITE float Qualcomm® SA8295P 13.213 ms 0 - 182 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.909 ms 0 - 48 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.166 ms 0 - 53 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.584 ms 0 - 74 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 2.769 ms 0 - 79 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 7.972 ms 0 - 13 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.336 ms 0 - 13 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.329 ms 0 - 2 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8775P 2.77 ms 0 - 54 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8650P 2.77 ms 0 - 54 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8255P 2.77 ms 0 - 54 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® QCS8450 2.769 ms 0 - 79 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 2.524 ms 0 - 13 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 21.968 ms 0 - 161 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 2.746 ms 0 - 48 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 1.166 ms 0 - 53 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA7255P 5.674 ms 0 - 49 MB NPU
Yolo-X TFLITE w8a8 Qualcomm® SA8295P 3.528 ms 0 - 48 MB NPU
Yolo-X TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.746 ms 0 - 48 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support