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 / README.md
qaihm-bot's picture
qaihm-bot
v0.53.1
b3bec7d verified
preview code
|
raw
history blame contribute delete
11 kB
metadata 
library_name: pytorch
license: other
tags:
  - backbone
  - bu_auto
  - real_time
  - android
pipeline_tag: image-classification

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 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 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 0.358 ms 0 - 38 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite Mobile 0.404 ms 0 - 40 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.845 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® X Elite 0.845 ms 12 - 12 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Gen 3 Mobile 0.5 ms 0 - 53 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS8550 (Proxy) 0.71 ms 1 - 3 MB NPU
MobileNet-v3-Large ONNX float Qualcomm® QCS9075 1.007 ms 1 - 3 MB NPU
MobileNet-v3-Large ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.404 ms 0 - 40 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.289 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite Mobile 0.367 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X2 Elite 0.311 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.848 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® X Elite 0.848 ms 6 - 6 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.47 ms 0 - 66 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS6490 56.392 ms 29 - 32 MB CPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.679 ms 0 - 10 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCS9075 0.863 ms 0 - 3 MB NPU
MobileNet-v3-Large ONNX w8a16 Qualcomm® QCM6690 20.238 ms 25 - 34 MB CPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.367 ms 0 - 41 MB NPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 14.333 ms 23 - 32 MB CPU
MobileNet-v3-Large ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 14.333 ms 23 - 32 MB CPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.427 ms 1 - 36 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite Mobile 0.523 ms 1 - 35 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X2 Elite 0.538 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.199 ms 1 - 1 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® X Elite 1.199 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 Qualcomm® QCS8275 (Proxy) 2.915 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.029 ms 1 - 25 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.352 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.352 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8775P 1.352 ms 1 - 33 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS9075 1.224 ms 1 - 3 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® QCS8450 (Proxy) 1.906 ms 0 - 56 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA7255P 2.915 ms 1 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Qualcomm® SA8295P 1.832 ms 0 - 31 MB NPU
MobileNet-v3-Large QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.523 ms 1 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.365 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.458 ms 0 - 36 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 1.116 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® X Elite 1.116 ms 0 - 0 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.661 ms 0 - 48 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS6490 2.803 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 2.052 ms 0 - 33 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.931 ms 0 - 2 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.147 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.147 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8775P 1.147 ms 0 - 35 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS9075 1.134 ms 2 - 4 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCM6690 4.009 ms 0 - 147 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 1.232 ms 0 - 51 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA7255P 2.052 ms 0 - 33 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Qualcomm® SA8295P 1.584 ms 0 - 32 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.458 ms 0 - 36 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.983 ms 0 - 33 MB NPU
MobileNet-v3-Large QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.983 ms 0 - 33 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.432 ms 0 - 40 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite Mobile 0.538 ms 0 - 41 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Gen 3 Mobile 0.697 ms 0 - 56 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8275 (Proxy) 3.089 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8550 (Proxy) 1.042 ms 0 - 128 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.407 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.407 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8775P 1.407 ms 0 - 37 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS9075 1.272 ms 0 - 15 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® QCS8450 (Proxy) 1.921 ms 0 - 59 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA7255P 3.089 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Qualcomm® SA8295P 1.868 ms 0 - 35 MB NPU
MobileNet-v3-Large TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.538 ms 0 - 41 MB NPU

License

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

References

Community