---
title: Mask2Former
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Mask2Former"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Mask2Former.md"
repository: Qualcomm-AI-Hub/Mask2Former
last_updated: 2026-10-16
license: apache-2.0
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
downloads: 0
stars: 0
tags:
  - android
---

# Mask2Former

> Mask2Former - Qualcomm-AI-Hub 在 ModelScope 开源的模型。Mask2Former: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/Mask2Former 是 ModelScope 魔搭社区上的image-segmentation模型，采用 apache-2.0 许可。

- **Repository**: Qualcomm-AI-Hub/Mask2Former
- **License**: apache-2.0
- **Tasks**: image-segmentation
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/Mask2Former

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/web-assets/model_demo.png)

# Mask2Former: Optimized for Qualcomm Devices

Mask2Former is a machine learning model that predicts masks and classes of objects in an image.

This is based on the implementation of Mask2Former found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/mask2former).
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/mask2former) 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
There are two ways to deploy this model on your device:

### Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_qcs8275.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_sa8775p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_qcs9075.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_sa7255p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_sa8295p.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/mask2former/releases/v0.62.1/mask2former-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)

For more device-specific assets and performance metrics, visit **[Mask2Former on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/mask2former)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/mask2former) 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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for [Mask2Former on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/mask2former) for usage instructions.

## Model Details

**Model Type:** Model_use_case.semantic_segmentation

**Model Stats:**
- Input resolution: 384x384
- Model checkpoint: facebook/mask2former-swin-tiny-coco-panoptic
- Number of output classes: 100

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 67.086 ms | 10 - 10 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 141.938 ms | 108 - 108 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 104.109 ms | 10 - 22 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 232.777 ms | 9 - 23 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 139.262 ms | 7 - 12 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 141.985 ms | 9 - 10 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 232.777 ms | 9 - 23 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 146.237 ms | 7 - 12 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 141.938 ms | 108 - 108 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 80.339 ms | 11 - 21 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 80.339 ms | 11 - 21 MB | NPU
| Mask2Former | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 70.089 ms | 10 - 17 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 67.407 ms | 2 - 2 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 142.67 ms | 2 - 2 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 103.751 ms | 4 - 11 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 233.28 ms | 2 - 12 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 139.18 ms | 2 - 9 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 138.614 ms | 2 - 4 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 147.004 ms | 2 - 10 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 147.004 ms | 2 - 10 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 147.004 ms | 2 - 10 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 233.28 ms | 2 - 12 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 146.009 ms | 2 - 9 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 142.67 ms | 2 - 2 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 80.306 ms | 3 - 11 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 289.925 ms | 2 - 11 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 181.801 ms | 2 - 7 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 80.306 ms | 3 - 11 MB | NPU
| Mask2Former | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 69.926 ms | 2 - 10 MB | NPU

## License
* The license for the original implementation of Mask2Former can be found
  [here](https://github.com/huggingface/transformers/blob/main/LICENSE).

## References
* [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527)
* [Source Model Implementation](https://github.com/huggingface/transformers/tree/main/src/transformers/models/mask2former)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).