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 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 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-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:

  • Input resolution: 224x224
  • Model checkpoint: Imagenet
  • Model size (float): 20.9 MB
  • Model size (w8a16): 6.35 MB
  • Number of parameters: 5.47M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v3-Large ONNX float Snapdragon® X2 Elite 0.329 ms 2 - 2 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.725 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.485 ms 0 - 53 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 1 Mobile 1.232 ms 1 - 60 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-8275 0.942 ms 1 - 4 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.708 ms 0 - 16 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8450 1.232 ms 1 - 60 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-9075 0.962 ms 1 - 3 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.725 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® Dragonwing™ Q-8750 0.4 ms 0 - 32 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Mobile 0.4 ms 0 - 32 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.36 ms 0 - 31 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X2 Elite 0.31 ms 1 - 1 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.703 ms 7 - 7 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.483 ms 0 - 62 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.981 ms 0 - 69 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 2.779 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.756 ms 0 - 4 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.697 ms 0 - 10 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8450 0.981 ms 0 - 69 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.84 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.703 ms 7 - 7 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 3.469 ms 0 - 158 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 0.766 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.352 ms 0 - 47 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Mobile 0.352 ms 0 - 47 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.292 ms 0 - 42 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.766 ms 0 - 43 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® X2 Elite 0.272 ms 1 - 1 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® X Elite 0.534 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.378 ms 0 - 65 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.73 ms 0 - 66 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.606 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.598 ms 0 - 4 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.525 ms 0 - 9 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® QCS8450 0.73 ms 0 - 66 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.655 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.534 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 1.986 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.542 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.334 ms 0 - 46 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Elite Mobile 0.334 ms 0 - 46 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.293 ms 0 - 44 MB NPU
MobileNet-v3-Large ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.542 ms 0 - 41 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.515 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.169 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.691 ms 0 - 55 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.898 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.138 ms 1 - 4 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 2.925 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.026 ms 1 - 2 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.376 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8650P 1.376 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8255P 1.376 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 1.898 ms 0 - 58 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.224 ms 3 - 5 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.169 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.52 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.925 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.841 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Mobile 0.52 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.427 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X2 Elite 0.504 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.085 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.66 ms 0 - 53 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.233 ms 0 - 59 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 3.35 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 0.95 ms 0 - 3 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 2.084 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.949 ms 0 - 8 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.156 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8650P 1.156 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8255P 1.156 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 1.233 ms 0 - 59 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.032 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.085 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 4.384 ms 0 - 151 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.021 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.462 ms 0 - 40 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.084 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.565 ms 0 - 37 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.462 ms 0 - 40 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.369 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.021 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® X2 Elite 0.315 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® X Elite 0.614 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.355 ms 0 - 50 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.725 ms 0 - 56 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.731 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.56 ms 0 - 3 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.182 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.512 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8775P 0.696 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8650P 0.696 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8255P 0.696 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® QCS8450 0.725 ms 0 - 56 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.582 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.614 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.241 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.564 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.259 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA7255P 1.182 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Qualcomm® SA8295P 0.996 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.259 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.217 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.564 ms 0 - 35 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 1.905 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.199 ms 0 - 16 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.051 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.032 ms 0 - 3 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 1.905 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.273 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® Dragonwing™ Q-8750 0.529 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.051 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.855 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 Snapdragon® 8 Elite Gen 5 Mobile 0.435 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.236 ms 0 - 50 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.54 ms 0 - 56 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.31 ms 0 - 10 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.58 ms 0 - 9 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.879 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.333 ms 0 - 2 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8775P 0.531 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8650P 0.531 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8255P 0.531 ms 0 - 36 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® QCS8450 0.54 ms 0 - 56 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.416 ms 0 - 8 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 1.685 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.396 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.196 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA7255P 0.879 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Qualcomm® SA8295P 0.779 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.196 ms 0 - 32 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.165 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.396 ms 0 - 32 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