Hugging Face's logo

qualcomm
/
MobileNet-v3-Small

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

MobileNet-v3-Small: Optimized for Qualcomm Devices

MobileNetV3Small 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-Small 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
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-Small 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-Small 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: 2.54M
  • Model size (float): 9.71 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MobileNet-v3-Small ONNX float Snapdragon® X2 Elite 0.262 ms 2 - 2 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® X Elite 0.556 ms 6 - 6 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Gen 3 Mobile 0.354 ms 1 - 45 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Gen 1 Mobile 0.863 ms 1 - 50 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.558 ms 0 - 8 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® QCS8450 0.863 ms 1 - 50 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ IQ-9075 0.709 ms 1 - 3 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.244 ms 0 - 29 MB NPU
MobileNet-v3-Small ONNX float Snapdragon® 8 Elite Mobile 0.289 ms 0 - 33 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ Q-8750 0.289 ms 0 - 33 MB NPU
MobileNet-v3-Small ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.556 ms 6 - 6 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® X2 Elite 0.437 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® X Elite 0.966 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.55 ms 0 - 43 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.574 ms 0 - 49 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® QCS8275 2.104 ms 1 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.836 ms 1 - 2 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8775P 1.096 ms 1 - 31 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8650P 1.096 ms 1 - 31 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8255P 1.096 ms 1 - 31 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® QCS8450 1.574 ms 0 - 49 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 0.976 ms 1 - 3 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.317 ms 1 - 30 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA7255P 2.104 ms 1 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Snapdragon® 8 Elite Mobile 0.412 ms 1 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® SA8295P 1.474 ms 0 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.412 ms 1 - 29 MB NPU
MobileNet-v3-Small QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 0.966 ms 1 - 1 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® X2 Elite 0.422 ms 0 - 0 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® X Elite 0.92 ms 0 - 0 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.55 ms 0 - 39 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 0.983 ms 0 - 46 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 2.754 ms 0 - 2 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® QCS8275 1.698 ms 0 - 28 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.796 ms 0 - 60 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8775P 0.994 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8650P 0.994 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8255P 0.994 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® QCS8450 0.983 ms 0 - 46 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 0.895 ms 2 - 4 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.799 ms 0 - 26 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.312 ms 0 - 28 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 2.803 ms 0 - 145 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA7255P 1.698 ms 0 - 28 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 0.371 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® SA8295P 1.298 ms 0 - 27 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 0.799 ms 0 - 26 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.371 ms 0 - 30 MB NPU
MobileNet-v3-Small QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.92 ms 0 - 0 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Gen 3 Mobile 0.562 ms 0 - 44 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Gen 1 Mobile 1.591 ms 0 - 51 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® QCS8275 2.166 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.835 ms 0 - 4 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8775P 1.131 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8650P 1.131 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8255P 1.131 ms 0 - 32 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® QCS8450 1.591 ms 0 - 51 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.004 ms 0 - 8 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.321 ms 0 - 31 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA7255P 2.166 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Snapdragon® 8 Elite Mobile 0.422 ms 0 - 34 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® SA8295P 1.476 ms 0 - 29 MB NPU
MobileNet-v3-Small TFLITE float Qualcomm® Dragonwing™ Q-8750 0.422 ms 0 - 34 MB NPU

License

  • The license for the original implementation of MobileNet-v3-Small 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

Model tree for qualcomm/MobileNet-v3-Small

Quantizations
1 model

Paper for qualcomm/MobileNet-v3-Small