---
title: ACT
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/ACT"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/ACT.md"
repository: Qualcomm-AI-Hub/ACT
last_updated: 2026-10-16
license: mit
pipeline_tag: robotics
tasks:
  - robotics
downloads: 0
stars: 0
tags:
  - android
---

# ACT

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

Qualcomm-AI-Hub/ACT 是 ModelScope 魔搭社区上的robotics模型，采用 mit 许可。

- **Repository**: Qualcomm-AI-Hub/ACT
- **License**: mit
- **Tasks**: robotics
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

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

---

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

# ACT: Optimized for Qualcomm Devices

ACT (Action Chunking with Transformers) is a robotic policy model that is trained to predict the next chunk of actions that the robotic hand is expected to perform.

This is based on the implementation of ACT found [here](https://github.com/tonyzhaozh/act).
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/act) 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 |
|---|---|---|---|---|
| ONNX | float | Universal | 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/act/releases/v0.62.1/act-onnx-float.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/act/releases/v0.62.1/act-qnn_dlc-float.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/act/releases/v0.62.1/act-tflite-float.zip)

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


### 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/act) 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 [ACT on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/act) for usage instructions.

## Model Details

**Model Type:** Model_use_case.robotics

**Model Stats:**
- Input resolution: 480x640
- Model checkpoint: act
- Model size (float): 255M
- Number of parameters: 83.92M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| ACT | ONNX | float | Snapdragon® X2 Elite | 6.763 ms | 4 - 4 MB | NPU
| ACT | ONNX | float | Snapdragon® X Elite | 12.835 ms | 64 - 64 MB | NPU
| ACT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.548 ms | 1 - 509 MB | NPU
| ACT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.447 ms | 4 - 320 MB | NPU
| ACT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 17.386 ms | 3 - 10 MB | NPU
| ACT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.304 ms | 0 - 388 MB | NPU
| ACT | ONNX | float | Qualcomm® QCS8450 | 19.447 ms | 4 - 320 MB | NPU
| ACT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 17.636 ms | 3 - 10 MB | NPU
| ACT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.835 ms | 64 - 64 MB | NPU
| ACT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 6.816 ms | 2 - 418 MB | NPU
| ACT | ONNX | float | Snapdragon® 8 Elite Mobile | 6.816 ms | 2 - 418 MB | NPU
| ACT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.944 ms | 3 - 449 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® X2 Elite | 5.312 ms | 4 - 4 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® X Elite | 10.936 ms | 4 - 4 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.945 ms | 0 - 335 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 20.842 ms | 2 - 261 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.442 ms | 4 - 9 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.294 ms | 4 - 6 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® SA8775P | 14.499 ms | 1 - 271 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® SA8650P | 14.499 ms | 1 - 271 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® SA8255P | 14.499 ms | 1 - 271 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® QCS8450 | 20.842 ms | 2 - 261 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 14.526 ms | 4 - 9 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.936 ms | 4 - 4 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.44 ms | 0 - 293 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® SA7255P | 44.85 ms | 2 - 295 MB | NPU
| ACT | QNN_DLC | float | Qualcomm® SA8295P | 16.562 ms | 0 - 210 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 5.44 ms | 0 - 293 MB | NPU
| ACT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.376 ms | 4 - 314 MB | NPU
| ACT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.109 ms | 0 - 413 MB | NPU
| ACT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 16.381 ms | 0 - 272 MB | NPU
| ACT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 14.432 ms | 0 - 72 MB | NPU
| ACT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.509 ms | 0 - 3 MB | NPU
| ACT | TFLITE | float | Qualcomm® SA8775P | 13.799 ms | 0 - 279 MB | NPU
| ACT | TFLITE | float | Qualcomm® SA8650P | 13.799 ms | 0 - 279 MB | NPU
| ACT | TFLITE | float | Qualcomm® SA8255P | 13.799 ms | 0 - 279 MB | NPU
| ACT | TFLITE | float | Qualcomm® QCS8450 | 16.381 ms | 0 - 272 MB | NPU
| ACT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 13.963 ms | 0 - 71 MB | NPU
| ACT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.738 ms | 0 - 282 MB | NPU
| ACT | TFLITE | float | Qualcomm® SA7255P | 44.756 ms | 0 - 327 MB | NPU
| ACT | TFLITE | float | Qualcomm® SA8295P | 15.716 ms | 0 - 207 MB | NPU
| ACT | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.738 ms | 0 - 282 MB | NPU
| ACT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.794 ms | 0 - 324 MB | NPU

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

## References
* [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://arxiv.org/abs/2304.13705)
* [Source Model Implementation](https://github.com/tonyzhaozh/act)

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