README.md

---
library_name: pytorch
license: agpl-3.0
tags:
- real_time
- android
pipeline_tag: object-detection

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_det/web-assets/model_demo.png)

# YOLOv8-Detection: Optimized for Mobile Deployment
## Real-time object detection optimized for mobile and edge by Ultralytics


Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of YOLOv8-Detection found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect).


 More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov8_det).

### Model Details

- **Model Type:** Object detection
- **Model Stats:**
  - Model checkpoint: YOLOv8-N
  - Input resolution: 640x640
  - Number of parameters: 3.18M
  - Model size: 12.2 MB

| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.826 ms | 0 - 13 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 4.472 ms | 5 - 16 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 5.425 ms | 5 - 31 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.21 ms | 0 - 38 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.157 ms | 5 - 45 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.546 ms | 2 - 56 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.395 ms | 0 - 34 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.431 ms | 5 - 39 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.029 ms | 1 - 38 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA7255P ADP | SA7255P | TFLITE | 71.971 ms | 0 - 27 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA7255P ADP | SA7255P | QNN | 69.017 ms | 4 - 13 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.851 ms | 0 - 12 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.139 ms | 5 - 7 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8295P ADP | SA8295P | TFLITE | 9.615 ms | 0 - 25 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8295P ADP | SA8295P | QNN | 7.728 ms | 1 - 19 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.788 ms | 0 - 14 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.026 ms | 5 - 8 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8775P ADP | SA8775P | TFLITE | 8.677 ms | 0 - 27 MB | FP16 | NPU | -- |
| YOLOv8-Detection | SA8775P ADP | SA8775P | QNN | 6.624 ms | 0 - 10 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 71.971 ms | 0 - 27 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 69.017 ms | 4 - 13 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.795 ms | 0 - 15 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.043 ms | 5 - 8 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 8.677 ms | 0 - 27 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 6.624 ms | 0 - 10 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 8.925 ms | 0 - 38 MB | FP16 | NPU | -- |
| YOLOv8-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.237 ms | 5 - 34 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.458 ms | 5 - 5 MB | FP16 | NPU | -- |
| YOLOv8-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.093 ms | 5 - 5 MB | FP16 | NPU | -- |




## License
* The license for the original implementation of YOLOv8-Detection can be found
  [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
* The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE)



## References
* [Ultralytics YOLOv8 Docs: Object Detection](https://docs.ultralytics.com/tasks/detect/)
* [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/detect)



## 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