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 | 16.487 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 13.543 ms | 3 - 12 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.41 ms | 0 - 47 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 8.419 ms | 5 - 46 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.677 ms | 0 - 21 MB | NPU | -- |
| YOLOv8-Detection | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 4.058 ms | 5 - 7 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.196 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 5.468 ms | 2 - 14 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.487 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 13.543 ms | 3 - 12 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 5.683 ms | 0 - 21 MB | NPU | -- |
| YOLOv8-Detection | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 3.989 ms | 5 - 7 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.605 ms | 0 - 26 MB | NPU | -- |
| YOLOv8-Detection | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 7.677 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 5.713 ms | 0 - 21 MB | NPU | -- |
| YOLOv8-Detection | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.987 ms | 6 - 9 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.196 ms | 0 - 40 MB | NPU | -- |
| YOLOv8-Detection | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 5.468 ms | 2 - 14 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.673 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.952 ms | 0 - 80 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.603 ms | 0 - 48 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.129 ms | 0 - 55 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.773 ms | 5 - 206 MB | NPU | -- |
| YOLOv8-Detection | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.018 ms | 0 - 177 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.018 ms | 0 - 48 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.582 ms | 5 - 99 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.639 ms | 1 - 88 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.378 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.891 ms | 5 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 7.632 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 4.598 ms | 2 - 44 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 3.89 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.479 ms | 2 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 15.169 ms | 2 - 14 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 7.632 ms | 1 - 11 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 4.022 ms | 2 - 6 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 5.23 ms | 0 - 17 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 3.911 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 4.479 ms | 2 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 3.9 ms | 2 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.881 ms | 2 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 2.546 ms | 2 - 46 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.442 ms | 0 - 75 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.886 ms | 2 - 42 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 6.005 ms | 2 - 76 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.447 ms | 2 - 2 MB | NPU | -- |
| YOLOv8-Detection | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.688 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 | 3.331 ms | 4 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 1.661 ms | 0 - 35 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 1.851 ms | 1 - 36 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.497 ms | 0 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.559 ms | 1 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.884 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 1.952 ms | 1 - 14 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 3.849 ms | 0 - 29 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 5.633 ms | 1 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 47.141 ms | 3 - 12 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 | 3.331 ms | 4 - 13 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.509 ms | 0 - 14 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.554 ms | 3 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2.329 ms | 0 - 23 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN | 2.344 ms | 1 - 18 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.51 ms | 0 - 14 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.555 ms | 2 - 5 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 1.884 ms | 0 - 22 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN | 1.952 ms | 1 - 14 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.508 ms | 0 - 15 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.568 ms | 1 - 12 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.526 ms | 0 - 28 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.987 ms | 0 - 32 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.024 ms | 1 - 34 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.886 ms | 1 - 81 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.92 ms | 0 - 24 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 0.889 ms | 1 - 32 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.31 ms | 1 - 78 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.839 ms | 1 - 1 MB | NPU | -- |
| YOLOv8-Detection | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.893 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