--- title: BEVFormer canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/BEVFormer" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/BEVFormer.md" repository: Qualcomm-AI-Hub/BEVFormer last_updated: 2026-10-16 license: apache-2.0 downloads: 0 stars: 0 tags: - bu_auto - android --- # BEVFormer > BEVFormer - Qualcomm-AI-Hub 在 ModelScope 开源的模型。BEVFormer: Optimized for Qualcomm Devices Qualcomm-AI-Hub/BEVFormer 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。 - **Repository**: Qualcomm-AI-Hub/BEVFormer - **License**: apache-2.0 - **Tags**: bu_auto, android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/BEVFormer --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/bevformer/web-assets/model_demo.png) # BEVFormer: Optimized for Qualcomm Devices Bevformer is a SOTA model of interest to the Auto BU. This is based on the implementation of BEVFormer found [here](https://github.com/fundamentalvision/BEVFormer/). 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/bevformer) 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/bevformer/releases/v0.62.1/bevformer-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/bevformer/releases/v0.62.1/bevformer-qnn_dlc-float.zip) For more device-specific assets and performance metrics, visit **[BEVFormer on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/bevformer)**. ### 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/bevformer) 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 [BEVFormer on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/bevformer) for usage instructions. ## Model Details **Model Type:** Model_use_case.driver_assistance **Model Stats:** - Input preprocessing: Images must be ImageNet mean/std normalized before inference; the model does not normalize internally. - Input resolution: 6 x 3 x 480 x 800 - Model checkpoint: bevformer_tiny_deformable_optimized_exp_86_epoch_24.pth - Model size: 120 MB - Number of parameters: 27M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | BEVFormer | ONNX | float | Snapdragon® X2 Elite | 1277.286 ms | 29 - 29 MB | NPU | BEVFormer | ONNX | float | Snapdragon® X Elite | 2394.933 ms | 51 - 51 MB | NPU | BEVFormer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1393.623 ms | 0 - 1124 MB | NPU | BEVFormer | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2236.206 ms | 26 - 1207 MB | NPU | BEVFormer | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2320.09 ms | 29 - 61 MB | NPU | BEVFormer | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1819.952 ms | 0 - 53 MB | NPU | BEVFormer | ONNX | float | Qualcomm® QCS8450 | 2236.206 ms | 26 - 1207 MB | NPU | BEVFormer | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1961.668 ms | 29 - 60 MB | NPU | BEVFormer | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2394.933 ms | 51 - 51 MB | NPU | BEVFormer | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1352.307 ms | 2 - 843 MB | NPU | BEVFormer | ONNX | float | Snapdragon® 8 Elite Mobile | 1352.307 ms | 2 - 843 MB | NPU | BEVFormer | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1223.467 ms | 0 - 860 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® X2 Elite | 1295.087 ms | 29 - 29 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® X Elite | 1946.029 ms | 29 - 29 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1667.489 ms | 29 - 1126 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1992.252 ms | 4 - 1097 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2347.891 ms | 29 - 62 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1880.741 ms | 29 - 34 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® SA8775P | 2011.958 ms | 26 - 863 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® SA8650P | 2011.958 ms | 26 - 863 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® SA8255P | 2011.958 ms | 26 - 863 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® QCS8450 | 1992.252 ms | 4 - 1097 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2013.791 ms | 29 - 62 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1946.029 ms | 29 - 29 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1266.836 ms | 26 - 913 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® SA7255P | 3964.374 ms | 26 - 855 MB | NPU | BEVFormer | QNN_DLC | float | Qualcomm® SA8295P | 2190.604 ms | 26 - 865 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1266.836 ms | 26 - 913 MB | NPU | BEVFormer | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1231.303 ms | 14 - 870 MB | NPU ## License * The license for the original implementation of BEVFormer can be found [here](https://github.com/fundamentalvision/BEVFormer/blob/master/LICENSE). ## References * [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://arxiv.org/abs/2203.17270) * [Source Model Implementation](https://github.com/fundamentalvision/BEVFormer/) ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).