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 | 16.804 ms | 0 - 28 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 13.542 ms | 1 - 10 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.845 ms | 0 - 35 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 7.114 ms | 5 - 42 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.759 ms | 0 - 14 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 4.009 ms | 5 - 7 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.286 ms | 0 - 29 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 5.568 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.804 ms | 0 - 28 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 13.542 ms | 1 - 10 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 5.792 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 4.049 ms | 5 - 8 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.641 ms | 0 - 26 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 7.696 ms | 2 - 19 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 5.788 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 4.037 ms | 5 - 8 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.286 ms | 0 - 29 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 5.568 ms | 2 - 16 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.824 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 4.01 ms | 5 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.226 ms | 4 - 24 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.178 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.815 ms | 0 - 41 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.593 ms | 1 - 54 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.053 ms | 0 - 34 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.615 ms | 5 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.768 ms | 5 - 42 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.498 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.121 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 7.68 ms | 2 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.911 ms | 2 - 40 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.931 ms | 2 - 6 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.539 ms | 0 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 14.918 ms | 2 - 17 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 7.68 ms | 2 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.958 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 5.191 ms | 0 - 18 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.954 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 4.539 ms | 0 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.936 ms | 2 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 9.332 ms | 2 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.593 ms | 2 - 40 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.699 ms | 0 - 47 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.266 ms | 2 - 39 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 6.311 ms | 2 - 46 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.332 ms | 2 - 2 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.611 ms | 1 - 1 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 3.335 ms | 0 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 3.351 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.843 ms | 0 - 32 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 1.998 ms | 1 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.507 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.59 ms | 1 - 4 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.897 ms | 0 - 23 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 1.95 ms | 1 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.639 ms | 0 - 31 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 5.904 ms | 1 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 50.964 ms | 2 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 3.335 ms | 0 - 20 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN | 3.351 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.511 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.571 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2.358 ms | 0 - 23 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN | 2.365 ms | 0 - 18 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.51 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.58 ms | 1 - 3 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.897 ms | 0 - 23 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN | 1.95 ms | 1 - 16 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.507 ms | 0 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.583 ms | 1 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.814 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.997 ms | 0 - 38 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.035 ms | 1 - 36 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.21 ms | 1 - 46 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.917 ms | 0 - 23 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 0.757 ms | 1 - 29 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.185 ms | 1 - 41 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.807 ms | 1 - 1 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.615 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