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 2.42, ONNX Runtime 1.25.0 Download
ONNX w8a16 Universal QAIRT 2.42, 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® 8 Elite Gen 5 Mobile 0.356 ms 0 - 39 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.721 ms 159 - 159 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.503 ms 0 - 56 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8550 (Proxy) 0.716 ms 0 - 47 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.403 ms 0 - 35 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS9075 1.011 ms 1 - 46 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8750 0.403 ms 0 - 35 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS7181 0.721 ms 159 - 159 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.29 ms 0 - 45 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.697 ms 149 - 149 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.474 ms 26 - 94 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS6490 56.364 ms 25 - 29 MB CPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.68 ms 0 - 47 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCM6690 20.238 ms 22 - 31 MB CPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 14.288 ms 24 - 33 MB CPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.367 ms 0 - 45 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS9075 0.864 ms 0 - 51 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS7790 14.288 ms 24 - 33 MB CPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8750 0.367 ms 0 - 45 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS7181 0.697 ms 149 - 149 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.425 ms 1 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.529 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.192 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.68 ms 0 - 55 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8275 2.918 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.033 ms 1 - 72 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.358 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8650P 1.358 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8255P 1.358 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 (Proxy) 1.904 ms 0 - 55 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.918 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.822 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.517 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS9075 1.22 ms 3 - 5 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8750 0.517 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS7181 1.192 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.358 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X2 Elite 0.501 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.092 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.658 ms 0 - 51 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS6490 2.789 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8275 2.068 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.932 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.145 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8650P 1.145 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8255P 1.145 ms 0 - 38 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCM6690 4.024 ms 0 - 150 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.068 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.983 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.599 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.456 ms 0 - 39 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS9075 1.137 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 1.225 ms 0 - 54 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS7790 0.983 ms 0 - 35 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 1.092 ms 0 - 0 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.431 ms 0 - 40 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 3 Mobile 0.702 ms 0 - 62 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8275 3.086 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8550 (Proxy) 1.043 ms 0 - 2 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.399 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8650P 1.399 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8255P 1.399 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8450 (Proxy) 1.941 ms 0 - 59 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.086 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.88 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.538 ms 0 - 40 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS9075 1.273 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8750 0.538 ms 0 - 40 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