--- library_name: pytorch license: other tags: - backbone - bu_auto - real_time - android pipeline_tag: image-classification --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/web-assets/model_demo.png) # MobileNet-v3-Large: Optimized for Qualcomm Devices MobileNet-v3-Large 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 MobileNet-v3-Large found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/mobilenet_v3_large) 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.com) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.47.0/mobilenet_v3_large-onnx-float.zip) | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.47.0/mobilenet_v3_large-onnx-w8a16.zip) | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.47.0/mobilenet_v3_large-qnn_dlc-float.zip) | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.47.0/mobilenet_v3_large-qnn_dlc-w8a16.zip) | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.47.0/mobilenet_v3_large-tflite-float.zip) For more device-specific assets and performance metrics, visit **[MobileNet-v3-Large on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_large)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/mobilenet_v3_large) 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 [MobileNet-v3-Large on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/mobilenet_v3_large) for usage instructions. ## Model Details **Model Type:** Model_use_case.image_classification **Model Stats:** - Model checkpoint: Imagenet - Input resolution: 224x224 - Number of parameters: 5.47M - Model size (float): 20.9 MB - Model size (w8a16): 6.35 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | MobileNet-v3-Large | ONNX | float | Snapdragon® X Elite | 0.864 ms | 12 - 12 MB | NPU | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.497 ms | 0 - 58 MB | NPU | MobileNet-v3-Large | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.711 ms | 1 - 2 MB | NPU | MobileNet-v3-Large | ONNX | float | Qualcomm® QCS9075 | 1.004 ms | 1 - 3 MB | NPU | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.401 ms | 0 - 34 MB | NPU | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.357 ms | 0 - 37 MB | NPU | MobileNet-v3-Large | ONNX | float | Snapdragon® X2 Elite | 0.336 ms | 13 - 13 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X Elite | 0.849 ms | 6 - 6 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.476 ms | 0 - 57 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCS6490 | 54.676 ms | 27 - 31 MB | CPU | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 0.682 ms | 0 - 36 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCS9075 | 0.862 ms | 0 - 3 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCM6690 | 20.309 ms | 23 - 32 MB | CPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.368 ms | 0 - 36 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 14.503 ms | 24 - 33 MB | CPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.292 ms | 0 - 41 MB | NPU | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X2 Elite | 0.319 ms | 6 - 6 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X Elite | 1.215 ms | 1 - 1 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.686 ms | 0 - 54 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.985 ms | 0 - 35 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.045 ms | 1 - 2 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8775P | 1.39 ms | 0 - 37 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS9075 | 1.224 ms | 1 - 3 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.906 ms | 0 - 58 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA7255P | 2.985 ms | 0 - 35 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8295P | 1.869 ms | 0 - 35 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.527 ms | 1 - 40 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.443 ms | 1 - 40 MB | NPU | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X2 Elite | 0.598 ms | 1 - 1 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.098 ms | 0 - 0 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.655 ms | 0 - 48 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 2.675 ms | 0 - 2 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 2.084 ms | 0 - 32 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 0.929 ms | 0 - 2 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.161 ms | 0 - 36 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.165 ms | 0 - 2 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 4.047 ms | 0 - 147 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 1.231 ms | 0 - 51 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.084 ms | 0 - 32 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.647 ms | 0 - 32 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.46 ms | 0 - 35 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.988 ms | 0 - 32 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.371 ms | 0 - 35 MB | NPU | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.531 ms | 0 - 0 MB | NPU | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.703 ms | 0 - 61 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 3.052 ms | 0 - 40 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.061 ms | 0 - 7 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8775P | 1.424 ms | 0 - 43 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS9075 | 1.273 ms | 0 - 15 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.935 ms | 0 - 64 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA7255P | 3.052 ms | 0 - 40 MB | NPU | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8295P | 1.881 ms | 0 - 41 MB | NPU | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.534 ms | 0 - 45 MB | NPU | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.443 ms | 0 - 45 MB | NPU ## License * The license for the original implementation of MobileNet-v3-Large can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE). ## References * [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244) * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).