---
title: YOLO26-Segmentation
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/YOLO26-Segmentation"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/YOLO26-Segmentation.md"
repository: Qualcomm-AI-Hub/YOLO26-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
---

# YOLO26-Segmentation

> YOLO26-Segmentation - Qualcomm-AI-Hub 在 ModelScope 开源的模型。YOLO26-Segmentation: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/YOLO26-Segmentation 是 ModelScope 魔搭社区上的image-segmentation模型，采用 agpl-3.0 许可。

- **Repository**: Qualcomm-AI-Hub/YOLO26-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/YOLO26-Segmentation

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/yolo26_seg/web-assets/model_demo.png)

# YOLO26-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLO26 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 YOLO26-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/yolo26_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/yolo26_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 [YOLO26-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/yolo26_seg) for usage instructions.


## Model Details

**Model Type:** Model_use_case.semantic_segmentation

**Model Stats:**
- Input resolution: 640x640
- Model checkpoint: YOLO26N-Seg
- Model size (float): 9.29 MB
- Model size (w8a16): 5.25 MB
- Number of output classes: 80
- Number of parameters: 2.7M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| YOLO26-Segmentation | ONNX | float | Snapdragon® X2 Elite | 4.109 ms | 17 - 17 MB | NPU
| YOLO26-Segmentation | ONNX | float | Snapdragon® X Elite | 8.095 ms | 17 - 17 MB | NPU
| YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.736 ms | 17 - 226 MB | NPU
| YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 16.355 ms | 17 - 242 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.188 ms | 15 - 19 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.186 ms | 10 - 22 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® QCS8450 | 16.355 ms | 17 - 242 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.721 ms | 15 - 18 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.095 ms | 17 - 17 MB | NPU
| YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.461 ms | 13 - 190 MB | NPU
| YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.461 ms | 13 - 190 MB | NPU
| YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.938 ms | 3 - 183 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.71 ms | 9 - 9 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.493 ms | 7 - 7 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.8 ms | 0 - 235 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.362 ms | 8 - 245 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.003 ms | 8 - 10 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.529 ms | 8 - 11 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.161 ms | 8 - 85 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® QCS8450 | 8.362 ms | 8 - 245 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.696 ms | 8 - 10 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.493 ms | 7 - 7 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 27.898 ms | 8 - 222 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.517 ms | 8 - 225 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.813 ms | 1 - 94 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.813 ms | 1 - 94 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.503 ms | 1 - 96 MB | NPU
| YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.517 ms | 8 - 225 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 3.46 ms | 5 - 5 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.569 ms | 5 - 5 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.871 ms | 5 - 188 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.887 ms | 4 - 206 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 6.594 ms | 5 - 16 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.088 ms | 5 - 7 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.794 ms | 0 - 161 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.794 ms | 0 - 161 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.794 ms | 0 - 161 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 10.887 ms | 4 - 206 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.587 ms | 5 - 15 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.569 ms | 5 - 5 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.213 ms | 5 - 163 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.845 ms | 1 - 159 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 10.992 ms | 1 - 175 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.213 ms | 5 - 163 MB | NPU
| YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.471 ms | 5 - 170 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.045 ms | 2 - 2 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.606 ms | 2 - 2 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.474 ms | 2 - 212 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.015 ms | 2 - 9 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.127 ms | 2 - 4 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.864 ms | 2 - 189 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.864 ms | 2 - 189 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.864 ms | 2 - 189 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.686 ms | 1 - 7 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.606 ms | 2 - 2 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 24.628 ms | 2 - 187 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 5.448 ms | 2 - 199 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.577 ms | 2 - 192 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.551 ms | 0 - 187 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.577 ms | 2 - 192 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.297 ms | 2 - 196 MB | NPU
| YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.448 ms | 2 - 199 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.101 ms | 3 - 193 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 11.427 ms | 4 - 210 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 7.044 ms | 4 - 24 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.416 ms | 4 - 7 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8775P | 7.186 ms | 4 - 170 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8650P | 7.186 ms | 4 - 170 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8255P | 7.186 ms | 4 - 170 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 11.427 ms | 4 - 210 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.849 ms | 4 - 23 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.215 ms | 0 - 163 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® SA7255P | 17.223 ms | 4 - 165 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8295P | 11.426 ms | 4 - 180 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.215 ms | 0 - 163 MB | NPU
| YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.759 ms | 0 - 167 MB | NPU

## License
* The license for the original implementation of YOLO26-Segmentation can be found
  [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).

## References
* [Ultralytics YOLO26 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).