README.md

---
library_name: pytorch
license: other
pipeline_tag: object-detection
tags:
- real_time
- android

---

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

# Yolo-NAS: Optimized for Mobile Deployment
## Real-time object detection optimized for mobile and edge


YoloNAS is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of Yolo-NAS found [here](https://github.com/Deci-AI/super-gradients).


 More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolonas).

### Model Details

- **Model Type:** Object detection
- **Model Stats:**
  - Model checkpoint: YoloNAS Small
  - Input resolution: 640x640
  - Number of parameters: 12.2M
  - Model size: 46.6 MB

| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 8.961 ms | 0 - 21 MB | FP16 | NPU | -- |
| Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 9.594 ms | 5 - 23 MB | FP16 | NPU | -- |
| Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 7.819 ms | 0 - 82 MB | FP16 | NPU | -- |
| Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 6.097 ms | 0 - 38 MB | FP16 | NPU | -- |
| Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 6.526 ms | 5 - 36 MB | FP16 | NPU | -- |
| Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.351 ms | 5 - 53 MB | FP16 | NPU | -- |
| Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 6.305 ms | 0 - 37 MB | FP16 | NPU | -- |
| Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 6.299 ms | 5 - 37 MB | FP16 | NPU | -- |
| Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 5.444 ms | 7 - 46 MB | FP16 | NPU | -- |
| Yolo-NAS | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 8.951 ms | 0 - 22 MB | FP16 | NPU | -- |
| Yolo-NAS | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 9.507 ms | 5 - 8 MB | FP16 | NPU | -- |
| Yolo-NAS | SA7255P ADP | SA7255P | QNN | 223.609 ms | 1 - 10 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 8.938 ms | 0 - 21 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8255 (Proxy) | SA8255P Proxy | QNN | 9.472 ms | 5 - 7 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8295P ADP | SA8295P | TFLITE | 13.91 ms | 0 - 35 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8295P ADP | SA8295P | QNN | 14.561 ms | 0 - 14 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 8.953 ms | 0 - 20 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8650 (Proxy) | SA8650P Proxy | QNN | 9.369 ms | 5 - 7 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8775P ADP | SA8775P | TFLITE | 15.522 ms | 0 - 32 MB | FP16 | NPU | -- |
| Yolo-NAS | SA8775P ADP | SA8775P | QNN | 16.293 ms | 1 - 11 MB | FP16 | NPU | -- |
| Yolo-NAS | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 12.218 ms | 0 - 37 MB | FP16 | NPU | -- |
| Yolo-NAS | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 12.833 ms | 5 - 37 MB | FP16 | NPU | -- |
| Yolo-NAS | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 10.306 ms | 5 - 5 MB | FP16 | NPU | -- |
| Yolo-NAS | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.473 ms | 22 - 22 MB | FP16 | NPU | -- |




## License
* The license for the original implementation of Yolo-NAS can be found
  [here](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md#license).
* The license for the compiled assets for on-device deployment can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/LICENSE.YOLONAS.md)



## References
* [A Next-Generation, Object Detection Foundational Model generated by Deci’s Neural Architecture Search Technology](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md)
* [Source Model Implementation](https://github.com/Deci-AI/super-gradients)



## Community
* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:[email protected]).

## Usage and Limitations

Model may not be used for or in connection with any of the following applications:

- Accessing essential private and public services and benefits;
- Administration of justice and democratic processes;
- Assessing or recognizing the emotional state of a person;
- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
- Education and vocational training;
- Employment and workers management;
- Exploitation of the vulnerabilities of persons resulting in harmful behavior;
- General purpose social scoring;
- Law enforcement;
- Management and operation of critical infrastructure;
- Migration, asylum and border control management;
- Predictive policing;
- Real-time remote biometric identification in public spaces;
- Recommender systems of social media platforms;
- Scraping of facial images (from the internet or otherwise); and/or
- Subliminal manipulation