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 (float): 17.9 MB
- Model size (w8a8): 4.68 MB
- Model size (w8a16): 5.03 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 | 22.267 ms | 0 - 43 MB | NPU | -- |
| Yolo-v6 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 14.869 ms | 0 - 74 MB | NPU | -- |
| Yolo-v6 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 12.907 ms | 0 - 41 MB | NPU | -- |
| Yolo-v6 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.409 ms | 5 - 40 MB | NPU | -- |
| Yolo-v6 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 10.748 ms | 0 - 15 MB | NPU | -- |
| Yolo-v6 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.501 ms | 5 - 33 MB | NPU | -- |
| Yolo-v6 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 12.667 ms | 0 - 43 MB | NPU | -- |
| Yolo-v6 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.25 ms | 2 - 69 MB | NPU | -- |
| Yolo-v6 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 22.267 ms | 0 - 43 MB | NPU | -- |
| Yolo-v6 | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 14.869 ms | 0 - 74 MB | NPU | -- |
| Yolo-v6 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 10.766 ms | 0 - 16 MB | NPU | -- |
| Yolo-v6 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.513 ms | 4 - 35 MB | NPU | -- |
| Yolo-v6 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 13.556 ms | 0 - 29 MB | NPU | -- |
| Yolo-v6 | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 6.94 ms | 4 - 32 MB | NPU | -- |
| Yolo-v6 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 11.0 ms | 0 - 20 MB | NPU | -- |
| Yolo-v6 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.523 ms | 5 - 31 MB | NPU | -- |
| Yolo-v6 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 12.667 ms | 0 - 43 MB | NPU | -- |
| Yolo-v6 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.25 ms | 2 - 69 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 10.699 ms | 0 - 15 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.549 ms | 3 - 34 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.658 ms | 0 - 53 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.393 ms | 0 - 56 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.225 ms | 5 - 111 MB | NPU | -- |
| Yolo-v6 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.086 ms | 0 - 153 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 6.368 ms | 0 - 50 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.949 ms | 5 - 76 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.575 ms | 5 - 103 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.995 ms | 0 - 0 MB | NPU | -- |
| Yolo-v6 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.043 ms | 6 - 6 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.226 ms | 2 - 28 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 2.752 ms | 2 - 39 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.171 ms | 2 - 9 MB | NPU | -- |
| Yolo-v6 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.755 ms | 2 - 30 MB | NPU | -- |
| Yolo-v6 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 8.671 ms | 0 - 30 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 5.226 ms | 2 - 28 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 2.173 ms | 2 - 12 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 3.299 ms | 0 - 34 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 2.188 ms | 2 - 10 MB | NPU | -- |
| Yolo-v6 | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 2.755 ms | 2 - 30 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.185 ms | 2 - 11 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.881 ms | 0 - 32 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.449 ms | 2 - 43 MB | NPU | -- |
| Yolo-v6 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.008 ms | 2 - 106 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.331 ms | 2 - 34 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.851 ms | 1 - 98 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.592 ms | 8 - 8 MB | NPU | -- |
| Yolo-v6 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.404 ms | 3 - 3 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 4.463 ms | 0 - 20 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.213 ms | 1 - 21 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2.263 ms | 0 - 37 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 1.677 ms | 1 - 33 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.069 ms | 0 - 29 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.347 ms | 1 - 29 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.501 ms | 0 - 21 MB | NPU | -- |
| Yolo-v6 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.677 ms | 1 - 22 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 4.615 ms | 0 - 30 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 4.771 ms | 1 - 27 MB | NPU | -- |
| Yolo-v6 | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 34.91 ms | 3 - 11 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 4.463 ms | 0 - 20 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 3.213 ms | 1 - 21 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2.076 ms | 0 - 30 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 1.351 ms | 1 - 28 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 3.026 ms | 0 - 22 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 2.296 ms | 1 - 27 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 2.067 ms | 0 - 29 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 1.348 ms | 1 - 28 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2.501 ms | 0 - 21 MB | NPU | -- |
| Yolo-v6 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 1.677 ms | 1 - 22 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.08 ms | 0 - 30 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 1.355 ms | 1 - 28 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.923 ms | 0 - 34 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.366 ms | 0 - 37 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.895 ms | 1 - 35 MB | NPU | -- |
| Yolo-v6 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 2.636 ms | 0 - 127 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.35 ms | 0 - 28 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.843 ms | 1 - 25 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.709 ms | 1 - 90 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.701 ms | 17 - 17 MB | NPU | -- |
| Yolo-v6 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.131 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