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

---

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

# Yolo-NAS-Quantized: Optimized for Mobile Deployment
## Quantized 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 post-training quantized to int8 using samples from the COCO dataset.

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


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

### Model Details

- **Model Type:** Object detection
- **Model Stats:**
  - Model checkpoint: YoloNAS Small
  - Input resolution: 640x640
  - Number of parameters: 12.2M
  - Model size: 12.1 MB

| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| Yolo-NAS-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.714 ms | 0 - 5 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.047 ms | 0 - 82 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.601 ms | 0 - 55 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 14.746 ms | 0 - 66 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.681 ms | 0 - 10 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.786 ms | 0 - 26 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 4.771 ms | 0 - 14 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.792 ms | 0 - 10 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | SA8295P ADP | SA8295P | TFLITE | 6.53 ms | 0 - 54 MB | INT8 | NPU | -- |
| Yolo-NAS-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.164 ms | 0 - 80 MB | INT8 | NPU | -- |




## License
* The license for the original implementation of Yolo-NAS-Quantized 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
* [YOLO-NAS by Deci Achieves SOTA Performance on Object Detection Using Neural Architecture Search](https://deci.ai/blog/yolo-nas-object-detection-foundation-model/)
* [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:ai-hub-support@qti.qualcomm.com).

## 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