---
title: YOLOv8-Segmentation
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/YOLOv8-Segmentation"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/YOLOv8-Segmentation.md"
repository: Qualcomm-AI-Hub/YOLOv8-Segmentation
last_updated: 2026-10-16
license: agpl-3.0
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
downloads: 0
stars: 0
tags:
  - real_time
  - android
---

# YOLOv8-Segmentation

> YOLOv8-Segmentation - Qualcomm-AI-Hub 在 ModelScope 开源的模型。YOLOv8-Segmentation: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/YOLOv8-Segmentation 是 ModelScope 魔搭社区上的image-segmentation模型，采用 agpl-3.0 许可。

- **Repository**: Qualcomm-AI-Hub/YOLOv8-Segmentation
- **License**: agpl-3.0
- **Tasks**: image-segmentation
- **Tags**: real_time, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/YOLOv8-Segmentation

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/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-cn/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.cn) 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-cn/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-cn/blob/main/src/qai_hub_models/models/yolov8_seg) for usage instructions.


## Model Details

**Model Type:** Model_use_case.semantic_segmentation

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

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.84 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 7.123 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.946 ms | 17 - 240 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.494 ms | 17 - 223 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.339 ms | 15 - 19 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.608 ms | 1 - 119 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8450 | 12.494 ms | 17 - 223 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.101 ms | 15 - 18 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.123 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.724 ms | 12 - 206 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.724 ms | 12 - 206 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.258 ms | 14 - 224 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.437 ms | 9 - 9 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 5.719 ms | 7 - 7 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.322 ms | 0 - 101 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 6.888 ms | 8 - 108 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.723 ms | 8 - 10 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 4.926 ms | 8 - 11 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.42 ms | 6 - 11 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® QCS8450 | 6.888 ms | 8 - 108 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.901 ms | 8 - 10 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.719 ms | 7 - 7 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 31.925 ms | 9 - 208 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.388 ms | 8 - 199 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.499 ms | 0 - 78 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.499 ms | 0 - 78 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.253 ms | 0 - 83 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.388 ms | 8 - 199 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® X2 Elite | 0.782 ms | 3 - 3 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® X Elite | 1.832 ms | 1 - 1 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.202 ms | 0 - 76 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.245 ms | 0 - 78 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 7.206 ms | 3 - 6 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.952 ms | 0 - 4 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.776 ms | 0 - 5 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® QCS8450 | 2.245 ms | 0 - 78 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.084 ms | 0 - 3 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.832 ms | 1 - 1 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 11.957 ms | 3 - 181 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 2.383 ms | 0 - 172 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.849 ms | 0 - 53 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.849 ms | 0 - 53 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.733 ms | 0 - 58 MB | NPU
| YOLOv8-Segmentation | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.383 ms | 0 - 172 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 3.135 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.027 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.441 ms | 5 - 212 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.381 ms | 5 - 199 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 6.406 ms | 5 - 16 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.645 ms | 5 - 6 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.528 ms | 0 - 182 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.528 ms | 0 - 182 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.528 ms | 0 - 182 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 9.381 ms | 5 - 199 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.257 ms | 5 - 15 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.027 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.804 ms | 0 - 180 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 17.144 ms | 1 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.397 ms | 0 - 166 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.804 ms | 0 - 180 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.062 ms | 5 - 200 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.995 ms | 2 - 2 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 4.296 ms | 2 - 2 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.545 ms | 2 - 81 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 4.907 ms | 2 - 83 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 14.729 ms | 1 - 7 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 3.824 ms | 2 - 9 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.792 ms | 2 - 4 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 4.5 ms | 1 - 59 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 4.5 ms | 1 - 59 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 4.5 ms | 1 - 59 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 4.907 ms | 2 - 83 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.266 ms | 0 - 6 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.296 ms | 2 - 2 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 22.874 ms | 2 - 176 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 5.552 ms | 2 - 177 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.759 ms | 0 - 58 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 7.848 ms | 1 - 58 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8295P | 5.171 ms | 0 - 55 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 1.759 ms | 0 - 58 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.446 ms | 2 - 66 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.552 ms | 2 - 177 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.924 ms | 1 - 1 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.84 ms | 1 - 1 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.093 ms | 1 - 54 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.021 ms | 1 - 60 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.508 ms | 1 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.689 ms | 1 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.586 ms | 1 - 6 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.058 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8650P | 2.058 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8255P | 2.058 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.021 ms | 1 - 60 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.826 ms | 1 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.84 ms | 1 - 1 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.683 ms | 1 - 163 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.842 ms | 0 - 42 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.793 ms | 0 - 38 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.802 ms | 1 - 41 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.525 ms | 1 - 39 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.793 ms | 0 - 38 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.668 ms | 1 - 40 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.842 ms | 0 - 42 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.017 ms | 0 - 109 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.686 ms | 4 - 90 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.915 ms | 4 - 24 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.072 ms | 4 - 6 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.995 ms | 4 - 88 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8650P | 5.995 ms | 4 - 88 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8255P | 5.995 ms | 4 - 88 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 8.686 ms | 4 - 90 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5.737 ms | 4 - 23 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.275 ms | 0 - 94 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.245 ms | 4 - 81 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.549 ms | 4 - 60 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.275 ms | 0 - 94 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.882 ms | 0 - 93 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.051 ms | 0 - 55 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.954 ms | 0 - 58 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.545 ms | 1 - 9 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.64 ms | 0 - 9 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.506 ms | 0 - 99 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 1.968 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 1.968 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 1.968 ms | 0 - 43 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.954 ms | 0 - 58 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.815 ms | 0 - 8 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.774 ms | 1 - 164 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.797 ms | 0 - 39 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.756 ms | 0 - 38 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 3.608 ms | 1 - 41 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 2.449 ms | 0 - 37 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.756 ms | 0 - 38 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.662 ms | 0 - 45 MB | NPU
| YOLOv8-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.797 ms | 0 - 39 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
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).