README.md

---
library_name: pytorch
license: other
tags:
- backbone
- bu_auto
- real_time
- android
pipeline_tag: image-classification

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/web-assets/model_demo.png)

# 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](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/mobilenet_v3_small) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.51.0/mobilenet_v3_small-onnx-float.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.51.0/mobilenet_v3_small-qnn_dlc-float.zip)
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.51.0/mobilenet_v3_small-qnn_dlc-w8a16.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.51.0/mobilenet_v3_small-tflite-float.zip)

For more device-specific assets and performance metrics, visit **[MobileNet-v3-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_small)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/mobilenet_v3_small) 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](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/mobilenet_v3_small) 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® 8 Elite Gen 5 Mobile | 0.243 ms | 0 - 33 MB | NPU
| MobileNet-v3-Small | ONNX | float | Snapdragon® X2 Elite | 0.25 ms | 5 - 5 MB | NPU
| MobileNet-v3-Small | ONNX | float | Snapdragon® X Elite | 0.685 ms | 5 - 5 MB | NPU
| MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.353 ms | 0 - 45 MB | NPU
| MobileNet-v3-Small | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.55 ms | 1 - 79 MB | NPU
| MobileNet-v3-Small | ONNX | float | Qualcomm® QCS9075 | 0.766 ms | 1 - 3 MB | NPU
| MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.292 ms | 0 - 28 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.319 ms | 1 - 33 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X2 Elite | 0.448 ms | 1 - 1 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X Elite | 0.989 ms | 1 - 1 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.546 ms | 0 - 43 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.094 ms | 1 - 29 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.832 ms | 0 - 5 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8775P | 1.088 ms | 1 - 31 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS9075 | 0.983 ms | 1 - 3 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.575 ms | 0 - 46 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA7255P | 2.094 ms | 1 - 29 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8295P | 1.454 ms | 0 - 29 MB | NPU
| MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.412 ms | 1 - 33 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.308 ms | 0 - 29 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.431 ms | 0 - 0 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.937 ms | 0 - 0 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.559 ms | 0 - 37 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 2.214 ms | 2 - 4 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 1.711 ms | 0 - 26 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 0.794 ms | 0 - 76 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8775P | 0.99 ms | 0 - 27 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 0.952 ms | 0 - 2 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 2.801 ms | 0 - 144 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 0.982 ms | 0 - 40 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA7255P | 1.711 ms | 0 - 26 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.302 ms | 0 - 24 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.372 ms | 0 - 29 MB | NPU
| MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.799 ms | 0 - 25 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.319 ms | 0 - 35 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.558 ms | 0 - 45 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2.168 ms | 0 - 30 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.833 ms | 0 - 10 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8775P | 1.156 ms | 0 - 32 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS9075 | 1.014 ms | 0 - 8 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.596 ms | 0 - 46 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® SA7255P | 2.168 ms | 0 - 30 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8295P | 1.49 ms | 0 - 29 MB | NPU
| MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.424 ms | 0 - 30 MB | NPU

## License
* The license for the original implementation of MobileNet-v3-Small can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).