---
title: Inception-v3
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Inception-v3"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/Inception-v3.md"
repository: Qualcomm-AI-Hub/Inception-v3
last_updated: 2026-10-16
license: bsd-3-clause
pipeline_tag: image-classification
tasks:
  - image-classification
downloads: 0
stars: 0
tags:
  - backbone
  - android
---

# Inception-v3

> Inception-v3 - Qualcomm-AI-Hub 在 ModelScope 开源的模型。Inception-v3: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/Inception-v3 是 ModelScope 魔搭社区上的image-classification模型，采用 bsd-3-clause 许可。

- **Repository**: Qualcomm-AI-Hub/Inception-v3
- **License**: bsd-3-clause
- **Tasks**: image-classification
- **Tags**: backbone, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/Inception-v3

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/inception_v3/web-assets/model_demo.png)

# Inception-v3: Optimized for Qualcomm Devices

InceptionNetV3 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of Inception-v3 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py).
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/inception_v3) 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/inception_v3/releases/v0.62.1/inception_v3-onnx-float.zip)
| ONNX | w8a8 | 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/inception_v3/releases/v0.62.1/inception_v3-onnx-w8a8.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/inception_v3/releases/v0.62.1/inception_v3-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/inception_v3/releases/v0.62.1/inception_v3-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/inception_v3/releases/v0.62.1/inception_v3-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/inception_v3/releases/v0.62.1/inception_v3-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[Inception-v3 on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/inception_v3)**.


### 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/inception_v3) 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 [Inception-v3 on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/inception_v3) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_classification

**Model Stats:**
- Input resolution: 224x224
- Model checkpoint: Imagenet
- Model size (float): 90.9 MB
- Model size (w8a8): 23.3 MB
- Number of parameters: 23.9M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| Inception-v3 | ONNX | float | Snapdragon® X2 Elite | 3.853 ms | 1 - 1 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® X Elite | 2.143 ms | 46 - 46 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.595 ms | 0 - 62 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 3.964 ms | 1 - 67 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.258 ms | 1 - 5 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.211 ms | 0 - 49 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® QCS8450 | 3.964 ms | 1 - 67 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 3.661 ms | 1 - 5 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.143 ms | 46 - 46 MB | NPU
| Inception-v3 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.338 ms | 0 - 40 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Elite Mobile | 1.338 ms | 0 - 40 MB | NPU
| Inception-v3 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.088 ms | 0 - 44 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.372 ms | 1 - 1 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® X Elite | 0.798 ms | 23 - 23 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.631 ms | 0 - 100 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.24 ms | 0 - 101 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 4.009 ms | 0 - 3 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.0 ms | 0 - 4 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.849 ms | 0 - 26 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® QCS8450 | 1.24 ms | 0 - 101 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.931 ms | 0 - 3 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.798 ms | 23 - 23 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.739 ms | 0 - 181 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.374 ms | 0 - 63 MB | NPU
| Inception-v3 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.539 ms | 0 - 65 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.539 ms | 0 - 65 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.424 ms | 0 - 62 MB | NPU
| Inception-v3 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.374 ms | 0 - 63 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® X2 Elite | 3.891 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® X Elite | 2.088 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.517 ms | 0 - 60 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.726 ms | 0 - 60 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.997 ms | 1 - 4 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.98 ms | 1 - 116 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8775P | 3.613 ms | 1 - 38 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8650P | 3.613 ms | 1 - 38 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8255P | 3.613 ms | 1 - 38 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® QCS8450 | 3.726 ms | 0 - 60 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 3.428 ms | 3 - 6 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.088 ms | 1 - 1 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.266 ms | 0 - 34 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA7255P | 13.481 ms | 1 - 35 MB | NPU
| Inception-v3 | QNN_DLC | float | Qualcomm® SA8295P | 4.166 ms | 0 - 33 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.266 ms | 0 - 34 MB | NPU
| Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.016 ms | 1 - 38 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.491 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.879 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.599 ms | 0 - 79 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.18 ms | 0 - 82 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 3.989 ms | 0 - 2 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.939 ms | 0 - 3 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.806 ms | 0 - 2 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.998 ms | 0 - 56 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.998 ms | 0 - 56 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.998 ms | 0 - 56 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.18 ms | 0 - 82 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.874 ms | 0 - 2 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.879 ms | 0 - 0 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.605 ms | 0 - 169 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.307 ms | 0 - 55 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.515 ms | 0 - 53 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 2.389 ms | 0 - 53 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.599 ms | 0 - 51 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.515 ms | 0 - 53 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.415 ms | 0 - 56 MB | NPU
| Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.307 ms | 0 - 55 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.489 ms | 0 - 118 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.729 ms | 0 - 121 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.977 ms | 0 - 50 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.035 ms | 0 - 3 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8775P | 3.622 ms | 0 - 69 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8650P | 3.622 ms | 0 - 69 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8255P | 3.622 ms | 0 - 69 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® QCS8450 | 3.729 ms | 0 - 121 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 3.429 ms | 0 - 49 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.27 ms | 0 - 69 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA7255P | 13.505 ms | 0 - 66 MB | NPU
| Inception-v3 | TFLITE | float | Qualcomm® SA8295P | 4.173 ms | 0 - 71 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.27 ms | 0 - 69 MB | NPU
| Inception-v3 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.01 ms | 0 - 70 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.644 ms | 0 - 79 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.288 ms | 0 - 83 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 4.287 ms | 0 - 25 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.007 ms | 0 - 26 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.908 ms | 0 - 31 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.175 ms | 0 - 55 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8650P | 1.175 ms | 0 - 55 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8255P | 1.175 ms | 0 - 55 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.288 ms | 0 - 83 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.053 ms | 0 - 25 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.71 ms | 0 - 168 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.408 ms | 0 - 53 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.547 ms | 0 - 57 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.527 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Qualcomm® SA8295P | 1.819 ms | 0 - 50 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.547 ms | 0 - 57 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.454 ms | 0 - 51 MB | NPU
| Inception-v3 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.408 ms | 0 - 53 MB | NPU

## License
* The license for the original implementation of Inception-v3 can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).

## References
* [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py)

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