YOLOv8-Detection-Quantized: Optimized for Mobile Deployment
Quantized 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 post-training quantized to int8 using samples from the COCO dataset.
This model is an implementation of YOLOv8-Detection-Quantized found here.
More details on model performance across various devices, can be found here.
Model Details
- Model Type: Object detection
- Model Stats:
- Model checkpoint: YOLOv8-N
- Input resolution: 640x640
- Number of parameters: 3.18M
- Model size: 3.26 MB
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| YOLOv8-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.926 ms | 0 - 11 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.007 ms | 0 - 3 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 6.403 ms | 0 - 25 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.286 ms | 0 - 33 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.436 ms | 0 - 20 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 4.582 ms | 1 - 56 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.213 ms | 0 - 30 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.479 ms | 1 - 35 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.576 ms | 0 - 46 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 11.745 ms | 0 - 21 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 12.005 ms | 1 - 9 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.91 ms | 0 - 12 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.006 ms | 0 - 2 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 2.81 ms | 0 - 22 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 3.317 ms | 1 - 13 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.914 ms | 0 - 11 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.01 ms | 0 - 3 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 2.86 ms | 0 - 20 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 3.133 ms | 1 - 8 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 4.805 ms | 0 - 30 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 6.511 ms | 1 - 13 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 49.652 ms | 3 - 12 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 11.745 ms | 0 - 21 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 12.005 ms | 1 - 9 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.92 ms | 0 - 11 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.013 ms | 1 - 4 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 2.86 ms | 0 - 20 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 3.133 ms | 1 - 8 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.106 ms | 0 - 31 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.517 ms | 1 - 33 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.304 ms | 1 - 1 MB | INT8 | NPU | -- |
| YOLOv8-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.054 ms | 5 - 5 MB | INT8 | NPU | -- |
License
- The license for the original implementation of YOLOv8-Detection-Quantized 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 is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The HF Inference API does not support object-detection models for pytorch library.