Hugging Face's logo

qualcomm
/
MobileNet-v3-Large

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community

MobileNet-v3-Large: Optimized for Qualcomm Devices

MobileNet-v3-Large 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-v3-Large 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
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit MobileNet-v3-Large 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-v3-Large 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: 5.47M
  • Model size (float): 20.9 MB
  • Model size (w8a16): 6.35 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v3-Large ONNX float Snapdragon® X2 Elite 0.327 ms 212 - 212 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.731 ms 148 - 148 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.487 ms 1 - 42 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 1 Mobile 1.249 ms 1 - 50 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8550 (Proxy) 0.71 ms 0 - 29 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8450 1.249 ms 1 - 50 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Mobile 0.405 ms 0 - 36 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.359 ms 1 - 28 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS9075 1.01 ms 1 - 46 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8750 0.405 ms 0 - 36 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS7181 0.731 ms 148 - 148 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X2 Elite 0.306 ms 212 - 212 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.698 ms 156 - 156 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.468 ms 0 - 50 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.945 ms 0 - 59 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS6490 2.292 ms 0 - 46 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.686 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8450 0.945 ms 0 - 59 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS9075 0.864 ms 0 - 51 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.291 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Mobile 0.363 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.731 ms 0 - 38 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCM6690 3.156 ms 0 - 153 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS7790 0.731 ms 0 - 38 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8750 0.363 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS7181 0.698 ms 156 - 156 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.539 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.172 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.681 ms 0 - 51 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.903 ms 0 - 60 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8275 2.939 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.027 ms 1 - 2 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 1.903 ms 0 - 60 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Mobile 0.52 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.854 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.425 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.939 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS9075 1.223 ms 1 - 3 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8750 0.52 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS7181 1.172 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X2 Elite 0.5 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.067 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.657 ms 0 - 51 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.219 ms 0 - 59 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS6490 2.571 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8275 2.052 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.933 ms 0 - 17 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 1.219 ms 0 - 59 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS9075 1.166 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.366 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.456 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.575 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.982 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCM6690 4.054 ms 0 - 150 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.052 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS7790 0.982 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8750 0.456 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS7181 1.067 ms 0 - 0 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 3 Mobile 0.697 ms 0 - 60 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 1 Mobile 1.919 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8275 3.103 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8550 (Proxy) 1.041 ms 0 - 26 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 3.643 ms 0 - 32 MB GPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8650P 3.643 ms 0 - 32 MB GPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8255P 3.643 ms 0 - 32 MB GPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8450 1.919 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Mobile 0.528 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.888 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.433 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.103 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS9075 1.272 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8750 0.528 ms 0 - 36 MB NPU

License

  • The license for the original implementation of MobileNet-v3-Large can be found here.

References

Community

Downloads last month

-

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

Paper for qualcomm/MobileNet-v3-Large