Hugging Face's logo

qualcomm
/
EfficientNet-Lite4

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community

EfficientNet-Lite4: Optimized for Qualcomm Devices

EfficientNet-Lite4 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 EfficientNet-Lite4 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 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit EfficientNet-Lite4 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 EfficientNet-Lite4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Input resolution: 300x300
  • Model checkpoint: Imagenet
  • Model size (float): 51.9 MB
  • Number of parameters: 13.01M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.139 ms 0 - 61 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.502 ms 0 - 58 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® X2 Elite 1.423 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® X Elite 2.754 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 3 Mobile 1.916 ms 0 - 104 MB NPU
EfficientNet-Lite4 ONNX float Snapdragon® 8 Gen 1 Mobile 5.325 ms 1 - 104 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-8275 4.619 ms 1 - 5 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.635 ms 0 - 49 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® QCS8450 5.325 ms 1 - 104 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-9075 4.139 ms 1 - 4 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.754 ms 29 - 29 MB NPU
EfficientNet-Lite4 ONNX float Qualcomm® Dragonwing™ Q-8750 1.502 ms 0 - 58 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.6 ms 0 - 79 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.701 ms 0 - 79 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X2 Elite 0.612 ms 1 - 1 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® X Elite 1.267 ms 15 - 15 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.866 ms 0 - 119 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.775 ms 2 - 123 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 5.222 ms 0 - 4 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.318 ms 0 - 4 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.224 ms 0 - 18 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® QCS8450 1.775 ms 2 - 123 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.416 ms 0 - 3 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.267 ms 15 - 15 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.727 ms 0 - 189 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.457 ms 0 - 76 MB NPU
EfficientNet-Lite4 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.701 ms 0 - 79 MB NPU
EfficientNet-Lite4 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.457 ms 0 - 76 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.25 ms 1 - 62 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.688 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X2 Elite 1.831 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® X Elite 3.523 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.197 ms 0 - 102 MB NPU
EfficientNet-Lite4 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.711 ms 0 - 100 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.851 ms 1 - 5 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.132 ms 1 - 38 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8650P 4.785 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8255P 4.785 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® QCS8450 6.711 ms 0 - 100 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 4.53 ms 1 - 4 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.523 ms 1 - 1 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.688 ms 1 - 55 MB NPU
EfficientNet-Lite4 QNN_DLC float Qualcomm® SA8295P 6.328 ms 1 - 53 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.513 ms 0 - 69 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.649 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® X2 Elite 0.744 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® X Elite 1.466 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.892 ms 0 - 100 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.959 ms 0 - 113 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.325 ms 0 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.318 ms 0 - 3 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.275 ms 0 - 2 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8650P 1.611 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8255P 1.611 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® QCS8450 1.959 ms 0 - 113 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.408 ms 2 - 5 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.466 ms 0 - 0 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 11.26 ms 0 - 183 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.595 ms 0 - 70 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.649 ms 0 - 67 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Qualcomm® SA8295P 2.398 ms 0 - 66 MB NPU
EfficientNet-Lite4 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.595 ms 0 - 70 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.25 ms 0 - 73 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.685 ms 0 - 72 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 3 Mobile 2.195 ms 0 - 113 MB NPU
EfficientNet-Lite4 TFLITE float Snapdragon® 8 Gen 1 Mobile 6.493 ms 0 - 115 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.841 ms 0 - 33 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.117 ms 0 - 6 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8650P 4.792 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8255P 4.792 ms 0 - 66 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® QCS8450 6.493 ms 0 - 115 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ IQ-9075 4.524 ms 0 - 33 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® Dragonwing™ Q-8750 1.685 ms 0 - 72 MB NPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA7255P 36.395 ms 0 - 28 MB GPU
EfficientNet-Lite4 TFLITE float Qualcomm® SA8295P 6.326 ms 0 - 52 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.413 ms 0 - 62 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.505 ms 0 - 67 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.642 ms 0 - 96 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.421 ms 0 - 109 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 4.678 ms 0 - 31 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.02 ms 0 - 18 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.91 ms 0 - 2 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8650P 1.278 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8255P 1.278 ms 0 - 63 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® QCS8450 1.421 ms 0 - 109 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.071 ms 0 - 18 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 10.059 ms 0 - 176 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.25 ms 0 - 170 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.505 ms 0 - 67 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA7255P 38.3 ms 1 - 27 MB GPU
EfficientNet-Lite4 TFLITE w8a8 Qualcomm® SA8295P 2.007 ms 0 - 60 MB NPU
EfficientNet-Lite4 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.25 ms 0 - 170 MB NPU

License

  • The license for the original implementation of EfficientNet-Lite4 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/EfficientNet-Lite4