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.
More details on model performance across various devices, can be found here.
Model Details
- Model Type: Model_use_case.object_detection
- Model Stats:
- Model checkpoint: YOLOv8-N
- Input resolution: 640x640
- Number of parameters: 3.18M
- Model size (float): 12.2 MB
- Model size (w8a8): 3.26 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 16.815 ms | 0 - 27 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 13.473 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.688 ms | 0 - 37 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 7.204 ms | 5 - 39 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.877 ms | 0 - 16 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.996 ms | 5 - 8 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.275 ms | 0 - 29 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 5.528 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.815 ms | 0 - 27 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 13.473 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 5.778 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 4.045 ms | 5 - 7 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.665 ms | 0 - 26 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 7.739 ms | 0 - 18 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 5.868 ms | 0 - 18 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 4.034 ms | 5 - 7 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.275 ms | 0 - 29 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 5.528 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.856 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 4.009 ms | 5 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.353 ms | 3 - 32 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.212 ms | 0 - 39 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.804 ms | 5 - 46 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.647 ms | 50 - 103 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.048 ms | 0 - 34 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.619 ms | 5 - 41 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.705 ms | 5 - 44 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.453 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.07 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 7.676 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.881 ms | 2 - 40 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.921 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.502 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 14.865 ms | 2 - 17 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 7.676 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.992 ms | 2 - 4 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 5.168 ms | 0 - 18 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.932 ms | 2 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 4.502 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.926 ms | 2 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 9.335 ms | 2 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.581 ms | 2 - 39 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.727 ms | 2 - 50 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.267 ms | 2 - 38 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 6.497 ms | 2 - 44 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.308 ms | 2 - 2 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.617 ms | 1 - 1 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.356 ms | 0 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 3.33 ms | 1 - 10 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.731 ms | 0 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 1.992 ms | 1 - 37 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.51 ms | 0 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.551 ms | 1 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.909 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 1.942 ms | 1 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.692 ms | 0 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 5.819 ms | 1 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 46.984 ms | 3 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3.356 ms | 0 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN | 3.33 ms | 1 - 10 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.512 ms | 0 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.576 ms | 1 - 4 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2.307 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN | 2.354 ms | 1 - 19 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.508 ms | 0 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.572 ms | 1 - 3 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.909 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN | 1.942 ms | 1 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.511 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.587 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.719 ms | 0 - 19 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.0 ms | 0 - 30 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.039 ms | 1 - 35 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.051 ms | 1 - 50 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.772 ms | 0 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 0.898 ms | 1 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.682 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.799 ms | 1 - 1 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.628 ms | 0 - 0 MB | NPU | -- |
License
- The license for the original implementation of YOLOv8-Detection can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
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
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support