Yolo-v6: Optimized for Mobile Deployment
Real-time object detection optimized for mobile and edge
YoloV6 is a machine learning model that predicts bounding boxes and classes of objects in an image.
This model is an implementation of Yolo-v6 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: YoloV6-N
- Input resolution: 640x640
- Number of parameters: 4.68M
- Model size: 17.9 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| Yolo-v6 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 21.849 ms | 0 - 38 MB | NPU | -- |
| Yolo-v6 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.795 ms | 3 - 12 MB | NPU | -- |
| Yolo-v6 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 12.708 ms | 0 - 38 MB | NPU | -- |
| Yolo-v6 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 7.544 ms | 5 - 39 MB | NPU | -- |
| Yolo-v6 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 10.482 ms | 0 - 9 MB | NPU | -- |
| Yolo-v6 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 4.484 ms | 5 - 8 MB | NPU | -- |
| Yolo-v6 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 12.335 ms | 0 - 39 MB | NPU | -- |
| Yolo-v6 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.277 ms | 2 - 16 MB | NPU | -- |
| Yolo-v6 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 21.849 ms | 0 - 38 MB | NPU | -- |
| Yolo-v6 | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 14.795 ms | 3 - 12 MB | NPU | -- |
| Yolo-v6 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 10.599 ms | 0 - 12 MB | NPU | -- |
| Yolo-v6 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 4.492 ms | 5 - 8 MB | NPU | -- |
| Yolo-v6 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 13.888 ms | 0 - 28 MB | NPU | -- |
| Yolo-v6 | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 7.083 ms | 0 - 18 MB | NPU | -- |
| Yolo-v6 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 10.72 ms | 0 - 10 MB | NPU | -- |
| Yolo-v6 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 4.616 ms | 5 - 7 MB | NPU | -- |
| Yolo-v6 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 12.335 ms | 0 - 39 MB | NPU | -- |
| Yolo-v6 | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 6.277 ms | 2 - 16 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 10.604 ms | 0 - 14 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 4.494 ms | 5 - 17 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.569 ms | 5 - 40 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.271 ms | 0 - 48 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 3.189 ms | 5 - 51 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.21 ms | 3 - 69 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 7.198 ms | 0 - 43 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.885 ms | 5 - 45 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.269 ms | 5 - 55 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.759 ms | 5 - 5 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.095 ms | 7 - 7 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 4.77 ms | 2 - 12 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 2.709 ms | 2 - 35 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.952 ms | 2 - 5 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 2.499 ms | 2 - 16 MB | NPU | -- |
| Yolo-v6 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 8.065 ms | 2 - 14 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN | 4.77 ms | 2 - 12 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.904 ms | 2 - 4 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN | 2.958 ms | 0 - 18 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.908 ms | 3 - 5 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN | 2.499 ms | 2 - 16 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.971 ms | 2 - 10 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.443 ms | 0 - 34 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.302 ms | 2 - 35 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.584 ms | 2 - 82 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 0.997 ms | 2 - 31 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.889 ms | 1 - 65 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.168 ms | 2 - 2 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.241 ms | 3 - 3 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 4.497 ms | 0 - 20 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 3.192 ms | 1 - 11 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2.432 ms | 0 - 37 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 1.836 ms | 1 - 35 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.073 ms | 0 - 27 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.356 ms | 1 - 4 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.474 ms | 0 - 22 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 1.656 ms | 1 - 16 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 4.361 ms | 0 - 31 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 4.623 ms | 1 - 15 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 32.946 ms | 3 - 12 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 4.497 ms | 0 - 20 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN | 3.192 ms | 1 - 11 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2.066 ms | 0 - 27 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.36 ms | 1 - 3 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2.932 ms | 0 - 23 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN | 2.357 ms | 0 - 18 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 2.07 ms | 0 - 27 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.35 ms | 1 - 4 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2.474 ms | 0 - 22 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN | 1.656 ms | 1 - 16 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.078 ms | 0 - 28 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.389 ms | 1 - 15 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.138 ms | 0 - 32 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.41 ms | 0 - 36 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 0.908 ms | 1 - 33 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.255 ms | 0 - 68 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.335 ms | 0 - 29 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 0.69 ms | 1 - 30 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.104 ms | 1 - 60 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.522 ms | 1 - 1 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.642 ms | 4 - 4 MB | NPU | -- |
License
- The license for the original implementation of Yolo-v6 can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
- YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
- Source Model Implementation
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