---
library_name: pytorch
license: other
tags:
- real_time
- android
pipeline_tag: image-segmentation

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_seg/web-assets/model_demo.png)

# YOLOv8-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.

This is based on the implementation of YOLOv8-Segmentation found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov8_seg) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started
Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov8_seg) Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations

See our repository for [YOLOv8-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/yolov8_seg) for usage instructions.


## Model Details

**Model Type:** Model_use_case.semantic_segmentation

**Model Stats:**
- Model checkpoint: YOLOv8N-Seg
- Input resolution: 640x640
- Number of output classes: 80
- Number of parameters: 3.43M
- Model size (float): 13.2 MB
- Model size (w8a16): 3.91 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.957 ms | 1 - 233 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.462 ms | 16 - 16 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 6.843 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.054 ms | 17 - 299 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.388 ms | 1 - 12 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS9075 | 7.781 ms | 12 - 15 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.308 ms | 1 - 222 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.992 ms | 1 - 196 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.813 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.99 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.444 ms | 0 - 206 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 17.109 ms | 0 - 179 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.58 ms | 5 - 6 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.505 ms | 1 - 182 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.05 ms | 5 - 15 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.281 ms | 5 - 196 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 17.109 ms | 0 - 179 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.408 ms | 0 - 166 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.783 ms | 0 - 181 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.835 ms | 0 - 99 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.01 ms | 0 - 108 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 16.304 ms | 4 - 83 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.104 ms | 4 - 7 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.941 ms | 4 - 88 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.868 ms | 3 - 22 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.567 ms | 4 - 86 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.304 ms | 4 - 83 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.665 ms | 4 - 60 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.259 ms | 0 - 84 MB | NPU

## License
* The license for the original implementation of YOLOv8-Segmentation can be found
  [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).

## References
* [Ultralytics YOLOv8 Docs: Instance Segmentation](https://docs.ultralytics.com/tasks/segment/)
* [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) 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).