MobileNet-v2: Optimized for Qualcomm Devices

MobileNetV2 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of MobileNet-v2 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 w8a16_mixed_int16 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
QNN_DLC w8a16_mixed_int16 Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MobileNet-v2 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 MobileNet-v2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 3.49M
  • Model size (float): 13.3 MB
  • Model size (w8a16): 4.39 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v2 ONNX float Snapdragon® X2 Elite 0.301 ms 180 - 180 MB NPU
MobileNet-v2 ONNX float Snapdragon® X Elite 0.634 ms 149 - 149 MB NPU
MobileNet-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 0.429 ms 1 - 40 MB NPU
MobileNet-v2 ONNX float Snapdragon® 8 Gen 1 Mobile 0.955 ms 1 - 46 MB NPU
MobileNet-v2 ONNX float Qualcomm® QCS8550 (Proxy) 0.637 ms 0 - 14 MB NPU
MobileNet-v2 ONNX float Qualcomm® QCS8450 0.955 ms 1 - 46 MB NPU
MobileNet-v2 ONNX float Snapdragon® 8 Elite Mobile 0.339 ms 0 - 29 MB NPU
MobileNet-v2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.277 ms 0 - 25 MB NPU
MobileNet-v2 ONNX float Qualcomm® QCS9075 0.895 ms 0 - 52 MB NPU
MobileNet-v2 ONNX float Qualcomm® QCS8750 0.339 ms 0 - 29 MB NPU
MobileNet-v2 ONNX float Qualcomm® QCS7181 0.634 ms 149 - 149 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® X2 Elite 0.252 ms 191 - 191 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® X Elite 0.557 ms 149 - 149 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.384 ms 51 - 90 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.707 ms 0 - 47 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS6490 1.792 ms 0 - 50 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.549 ms 0 - 9 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS8450 0.707 ms 0 - 47 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.219 ms 0 - 32 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® 8 Elite Mobile 0.271 ms 0 - 39 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS9075 0.733 ms 0 - 49 MB NPU
MobileNet-v2 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.602 ms 0 - 31 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCM6690 2.705 ms 0 - 146 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS7790 0.602 ms 0 - 31 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS8750 0.271 ms 0 - 39 MB NPU
MobileNet-v2 ONNX w8a16 Qualcomm® QCS7181 0.557 ms 149 - 149 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® X2 Elite 0.289 ms 181 - 181 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® X Elite 0.615 ms 160 - 160 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.427 ms 0 - 39 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 0.6 ms 0 - 15 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCM6690 3.864 ms 0 - 146 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.253 ms 0 - 37 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCS9075 0.779 ms 0 - 50 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.321 ms 0 - 41 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 0.731 ms 0 - 145 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCS7790 0.731 ms 0 - 145 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCS8750 0.321 ms 0 - 41 MB NPU
MobileNet-v2 ONNX w8a16_mixed_int16 Qualcomm® QCS7181 0.615 ms 160 - 160 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® X2 Elite 0.239 ms 213 - 213 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® X Elite 0.454 ms 155 - 155 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.323 ms 0 - 37 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.593 ms 0 - 44 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS6490 1.252 ms 0 - 45 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.46 ms 0 - 8 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS8450 0.593 ms 0 - 44 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS9075 0.581 ms 0 - 49 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCM6690 1.498 ms 0 - 30 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.448 ms 0 - 31 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.247 ms 0 - 31 MB NPU
MobileNet-v2 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.284 ms 0 - 34 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS7790 0.448 ms 0 - 31 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS8750 0.284 ms 0 - 34 MB NPU
MobileNet-v2 ONNX w8a8 Qualcomm® QCS7181 0.454 ms 155 - 155 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® X2 Elite 0.47 ms 1 - 1 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® X Elite 1.062 ms 1 - 1 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.607 ms 0 - 49 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.699 ms 0 - 55 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS8275 2.679 ms 1 - 29 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.922 ms 1 - 3 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS8450 1.699 ms 0 - 55 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® 8 Elite Mobile 0.448 ms 1 - 35 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® SA7255P 2.679 ms 1 - 29 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® SA8295P 1.488 ms 0 - 28 MB NPU
MobileNet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.345 ms 1 - 31 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS9075 1.125 ms 1 - 3 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS8750 0.448 ms 1 - 35 MB NPU
MobileNet-v2 QNN_DLC float Qualcomm® QCS7181 1.062 ms 1 - 1 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® X2 Elite 0.423 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® X Elite 0.926 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.56 ms 0 - 43 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 0.982 ms 0 - 48 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS6490 2.315 ms 0 - 2 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS8275 1.772 ms 0 - 30 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.796 ms 0 - 2 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS8450 0.982 ms 0 - 48 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.29 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.367 ms 0 - 36 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS9075 0.983 ms 2 - 4 MB NPU
MobileNet-v2 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.863 ms 0 - 143 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCM6690 3.324 ms 0 - 144 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® SA8295P 1.266 ms 0 - 29 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® SA7255P 1.772 ms 0 - 30 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS7790 0.863 ms 0 - 143 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS8750 0.367 ms 0 - 36 MB NPU
MobileNet-v2 QNN_DLC w8a16 Qualcomm® QCS7181 0.926 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® X2 Elite 0.464 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® X Elite 1.001 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Gen 3 Mobile 0.602 ms 0 - 44 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8275 2.005 ms 0 - 32 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8550 (Proxy) 0.856 ms 0 - 7 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCM6690 4.773 ms 0 - 145 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Gen 5 Mobile 0.323 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS9075 1.029 ms 0 - 2 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® 8 Elite Mobile 0.414 ms 0 - 32 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Snapdragon® 7 Gen 4 Mobile 0.975 ms 0 - 143 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® SA7255P 2.005 ms 0 - 32 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS7790 0.975 ms 0 - 143 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS8750 0.414 ms 0 - 32 MB NPU
MobileNet-v2 QNN_DLC w8a16_mixed_int16 Qualcomm® QCS7181 1.001 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.269 ms 0 - 0 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® X Elite 0.553 ms 1 - 1 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.312 ms 0 - 43 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.631 ms 0 - 49 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS6490 1.387 ms 0 - 2 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS8275 1.105 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.453 ms 0 - 8 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS8450 0.631 ms 0 - 49 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS9075 0.548 ms 0 - 2 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® SA7255P 1.105 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCM6690 1.771 ms 0 - 30 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.48 ms 1 - 30 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® SA8295P 0.807 ms 0 - 29 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.188 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.226 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS7790 0.48 ms 1 - 30 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS8750 0.226 ms 0 - 31 MB NPU
MobileNet-v2 QNN_DLC w8a8 Qualcomm® QCS7181 0.553 ms 1 - 1 MB NPU
MobileNet-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.601 ms 0 - 53 MB NPU
MobileNet-v2 TFLITE float Snapdragon® 8 Gen 1 Mobile 1.701 ms 0 - 57 MB NPU
MobileNet-v2 TFLITE float Qualcomm® QCS8275 2.703 ms 0 - 34 MB NPU
MobileNet-v2 TFLITE float Qualcomm® QCS8550 (Proxy) 0.926 ms 0 - 2 MB NPU
MobileNet-v2 TFLITE float Qualcomm® SA8775P 3.385 ms 0 - 28 MB GPU
MobileNet-v2 TFLITE float Qualcomm® SA8650P 3.385 ms 0 - 28 MB GPU
MobileNet-v2 TFLITE float Qualcomm® SA8255P 3.385 ms 0 - 28 MB GPU
MobileNet-v2 TFLITE float Qualcomm® QCS8450 1.701 ms 0 - 57 MB NPU
MobileNet-v2 TFLITE float Snapdragon® 8 Elite Mobile 0.449 ms 0 - 32 MB NPU
MobileNet-v2 TFLITE float Qualcomm® SA7255P 2.703 ms 0 - 34 MB NPU
MobileNet-v2 TFLITE float Qualcomm® SA8295P 1.506 ms 0 - 30 MB NPU
MobileNet-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.345 ms 0 - 35 MB NPU
MobileNet-v2 TFLITE float Qualcomm® QCS9075 1.129 ms 0 - 10 MB NPU
MobileNet-v2 TFLITE float Qualcomm® QCS8750 0.449 ms 0 - 32 MB NPU
MobileNet-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.29 ms 0 - 43 MB NPU
MobileNet-v2 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.539 ms 0 - 52 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS6490 1.128 ms 0 - 7 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS8275 0.965 ms 0 - 33 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.412 ms 0 - 2 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® SA8775P 3.83 ms 0 - 29 MB GPU
MobileNet-v2 TFLITE w8a8 Qualcomm® SA8650P 3.83 ms 0 - 29 MB GPU
MobileNet-v2 TFLITE w8a8 Qualcomm® SA8255P 3.83 ms 0 - 29 MB GPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS8450 0.539 ms 0 - 52 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS9075 0.574 ms 0 - 6 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® SA7255P 0.965 ms 0 - 33 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCM6690 1.641 ms 0 - 30 MB NPU
MobileNet-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.415 ms 0 - 30 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® SA8295P 0.806 ms 0 - 29 MB NPU
MobileNet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.186 ms 0 - 32 MB NPU
MobileNet-v2 TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.215 ms 0 - 30 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS7790 0.415 ms 0 - 30 MB NPU
MobileNet-v2 TFLITE w8a8 Qualcomm® QCS8750 0.215 ms 0 - 30 MB NPU

License

  • The license for the original implementation of MobileNet-v2 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

Model tree for qualcomm/MobileNet-v2

Finetunes
2 models

Paper for qualcomm/MobileNet-v2