--- title: RepViT canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/RepViT" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/RepViT.md" repository: Qualcomm-AI-Hub/RepViT last_updated: 2026-10-16 license: apache-2.0 pipeline_tag: image-classification tasks: - image-classification downloads: 0 stars: 0 tags: - backbone - android --- # RepViT > RepViT - Qualcomm-AI-Hub 在 ModelScope 开源的模型。RepViT: Optimized for Qualcomm Devices Qualcomm-AI-Hub/RepViT 是 ModelScope 魔搭社区上的image-classification模型，采用 apache-2.0 许可。 - **Repository**: Qualcomm-AI-Hub/RepViT - **License**: apache-2.0 - **Tasks**: image-classification - **Tags**: backbone, android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/RepViT --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/repvit/web-assets/model_demo.png) # RepViT: Optimized for Qualcomm Devices RepViT is a lightweight pure CNN model for mobile devices, incorporating efficient architectural designs from Vision Transformers into CNNs. It achieves over 80% top-1 accuracy on ImageNet with 1ms latency on an iPhone 12. This is based on the implementation of RepViT found [here](https://github.com/THU-MIG/RepViT). 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/repvit) 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/repvit/releases/v0.62.1/repvit-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/repvit/releases/v0.62.1/repvit-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/repvit/releases/v0.62.1/repvit-tflite-float.zip) For more device-specific assets and performance metrics, visit **[RepViT on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/repvit)**. ### 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/repvit) 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 [RepViT on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/repvit) for usage instructions. ## Model Details **Model Type:** Model_use_case.image_classification **Model Stats:** - Input resolution: 224x224 - Model checkpoint: Imagenet - Model size (float): 91 MB - Number of parameters: 22.9M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | RepViT | ONNX | float | Snapdragon® X2 Elite | 1.699 ms | 2 - 2 MB | NPU | RepViT | ONNX | float | Snapdragon® X Elite | 3.324 ms | 47 - 47 MB | NPU | RepViT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.384 ms | 0 - 196 MB | NPU | RepViT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 11.538 ms | 1 - 193 MB | NPU | RepViT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.633 ms | 0 - 4 MB | NPU | RepViT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.184 ms | 0 - 49 MB | NPU | RepViT | ONNX | float | Qualcomm® QCS8450 | 11.538 ms | 1 - 193 MB | NPU | RepViT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.327 ms | 0 - 4 MB | NPU | RepViT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.324 ms | 47 - 47 MB | NPU | RepViT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.796 ms | 0 - 112 MB | NPU | RepViT | ONNX | float | Snapdragon® 8 Elite Mobile | 1.796 ms | 0 - 112 MB | NPU | RepViT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.452 ms | 0 - 114 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® X2 Elite | 2.053 ms | 1 - 1 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® X Elite | 3.895 ms | 1 - 1 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.567 ms | 0 - 179 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 12.253 ms | 0 - 177 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.768 ms | 1 - 4 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.505 ms | 1 - 166 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® SA8775P | 4.848 ms | 1 - 103 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® SA8650P | 4.848 ms | 1 - 103 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® SA8255P | 4.848 ms | 1 - 103 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® QCS8450 | 12.253 ms | 0 - 177 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.579 ms | 1 - 3 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.895 ms | 1 - 1 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.903 ms | 1 - 103 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® SA7255P | 14.438 ms | 1 - 102 MB | NPU | RepViT | QNN_DLC | float | Qualcomm® SA8295P | 9.646 ms | 1 - 106 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.903 ms | 1 - 103 MB | NPU | RepViT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.504 ms | 1 - 104 MB | NPU | RepViT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.556 ms | 0 - 231 MB | NPU | RepViT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 12.274 ms | 0 - 226 MB | NPU | RepViT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.766 ms | 0 - 51 MB | NPU | RepViT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.47 ms | 0 - 2 MB | NPU | RepViT | TFLITE | float | Qualcomm® SA8775P | 4.869 ms | 0 - 164 MB | NPU | RepViT | TFLITE | float | Qualcomm® SA8650P | 4.869 ms | 0 - 164 MB | NPU | RepViT | TFLITE | float | Qualcomm® SA8255P | 4.869 ms | 0 - 164 MB | NPU | RepViT | TFLITE | float | Qualcomm® QCS8450 | 12.274 ms | 0 - 226 MB | NPU | RepViT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.584 ms | 0 - 50 MB | NPU | RepViT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.886 ms | 0 - 164 MB | NPU | RepViT | TFLITE | float | Qualcomm® SA7255P | 14.436 ms | 0 - 162 MB | NPU | RepViT | TFLITE | float | Qualcomm® SA8295P | 9.668 ms | 0 - 161 MB | NPU | RepViT | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.886 ms | 0 - 164 MB | NPU | RepViT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.514 ms | 0 - 166 MB | NPU ## License * The license for the original implementation of RepViT can be found [here](https://github.com/THU-MIG/RepViT/blob/main/LICENSE). ## References * [RepViT: Revisiting Mobile CNN From ViT Perspective](https://arxiv.org/abs/2307.09283) * [Source Model Implementation](https://github.com/THU-MIG/RepViT) ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).