---
library_name: pytorch
license: apache-2.0
tags:
- real_time
- android
pipeline_tag: object-detection

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmdet/web-assets/model_demo.png)

# RTMDet: Optimized for Mobile Deployment
## Real-time object detection optimized for mobile and edge


RTMDet is a highly efficient model for real-time object detection,capable of predicting both the bounding boxes and classes of objects within an image.It is highly optimized for real-time applications, making it reliable for industrial and commercial use

This model is an implementation of RTMDet found [here](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet).


 More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/rtmdet).

### Model Details

- **Model Type:** Object detection
- **Model Stats:**
  - Model checkpoint: RTMDet Medium
  - Input resolution: 640x640
  - Number of parameters: 27.5M
  - Model size: 105 MB

| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| RTMDet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 16.655 ms | 0 - 16 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 16.756 ms | 1 - 150 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 12.399 ms | 0 - 102 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 12.989 ms | 5 - 44 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.629 ms | 0 - 64 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 11.77 ms | 5 - 36 MB | FP16 | NPU | -- |
| RTMDet | SA7255P ADP | SA7255P | TFLITE | 578.983 ms | 0 - 62 MB | FP16 | NPU | -- |
| RTMDet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 16.501 ms | 0 - 14 MB | FP16 | NPU | -- |
| RTMDet | SA8295P ADP | SA8295P | TFLITE | 34.28 ms | 0 - 70 MB | FP16 | NPU | -- |
| RTMDet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 16.418 ms | 0 - 12 MB | FP16 | NPU | -- |
| RTMDet | SA8775P ADP | SA8775P | TFLITE | 29.382 ms | 0 - 61 MB | FP16 | NPU | -- |
| RTMDet | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 578.983 ms | 0 - 62 MB | FP16 | NPU | -- |
| RTMDet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 15.949 ms | 0 - 15 MB | FP16 | NPU | -- |
| RTMDet | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 29.382 ms | 0 - 61 MB | FP16 | NPU | -- |
| RTMDet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 31.458 ms | 0 - 110 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 17.03 ms | 48 - 48 MB | FP16 | NPU | -- |




## License
* The license for the original implementation of RTMDet can be found
  [here](https://github.com/open-mmlab/mmdetection/blob/3.x/LICENSE).
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)



## References
* [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://github.com/open-mmlab/mmdetection/blob/3.x/README.md)
* [Source Model Implementation](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet)



## Community
* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).

## 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