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 0.326 ms 2 - 2 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.73 ms 13 - 13 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.489 ms 0 - 52 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 1 Mobile 1.231 ms 1 - 61 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.709 ms 0 - 16 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8450 1.231 ms 1 - 61 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-9075 0.963 ms 1 - 3 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.36 ms 0 - 31 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Mobile 0.401 ms 0 - 30 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ Q-8750 0.401 ms 0 - 30 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.73 ms 13 - 13 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X2 Elite 0.308 ms 1 - 1 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.708 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.472 ms 0 - 61 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.951 ms 0 - 68 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 2.829 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.683 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8450 0.951 ms 0 - 68 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.797 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.727 ms 0 - 42 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.292 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 3.199 ms 0 - 157 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Mobile 0.361 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 0.727 ms 0 - 42 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.361 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.708 ms 6 - 6 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.512 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.187 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.686 ms 0 - 51 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.899 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8275 2.927 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.022 ms 1 - 2 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.357 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8650P 1.357 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8255P 1.357 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 1.899 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.235 ms 1 - 3 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.428 ms 1 - 34 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.927 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Mobile 0.517 ms 1 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.828 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.517 ms 1 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.187 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X2 Elite 0.502 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.073 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.657 ms 0 - 50 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.221 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 3.191 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8275 2.081 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.933 ms 0 - 64 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.151 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8650P 1.151 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8255P 1.151 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 1.221 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.029 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.992 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.367 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 4.021 ms 0 - 150 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.081 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.459 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.562 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 0.992 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.459 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.073 ms 0 - 0 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 3 Mobile 0.699 ms 0 - 55 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 1 Mobile 1.92 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8275 3.12 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.039 ms 0 - 17 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.407 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8650P 1.407 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8255P 1.407 ms 0 - 38 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8450 1.92 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.274 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.435 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.12 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Mobile 0.529 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.869 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ Q-8750 0.529 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