--- title: StateTransformer canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/StateTransformer" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/StateTransformer.md" repository: Qualcomm-AI-Hub/StateTransformer last_updated: 2026-10-16 license: mit downloads: 0 stars: 0 tags: - bu_auto - android --- # StateTransformer > StateTransformer - Qualcomm-AI-Hub 在 ModelScope 开源的模型。StateTransformer: Optimized for Qualcomm Devices Qualcomm-AI-Hub/StateTransformer 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。 - **Repository**: Qualcomm-AI-Hub/StateTransformer - **License**: mit - **Tags**: bu_auto, android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/StateTransformer --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/statetransformer/web-assets/model_demo.png) # StateTransformer: Optimized for Qualcomm Devices StateTransformer is a transformer-based model designed for trajectory prediction in self-driving scenarios. It integrates rasterized map data, agent context, and temporal dynamics to generate accurate future trajectories. 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/statetransformer) 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/statetransformer/releases/v0.62.1/statetransformer-onnx-float.zip) | TFLITE | float | Universal | | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/statetransformer/releases/v0.62.1/statetransformer-tflite-float.zip) For more device-specific assets and performance metrics, visit **[StateTransformer on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/statetransformer)**. ### 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/statetransformer) 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 [StateTransformer on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/statetransformer) for usage instructions. ## Model Details **Model Type:** Model_use_case.driver_assistance **Model Stats:** - Input resolution: 1x224x224x58, 1x224x224x58, 1x4x7 - Model checkpoint: pretrained-mixtral-small - Model size (float): 348 MB - Number of parameters: 90.7M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | StateTransformer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 291.136 ms | 200 - 5703 MB | NPU | StateTransformer | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 349.435 ms | 100 - 142 MB | NPU | StateTransformer | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 373.184 ms | 196 - 200 MB | NPU | StateTransformer | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 315.741 ms | 106 - 147 MB | NPU | StateTransformer | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 236.364 ms | 168 - 5681 MB | NPU | StateTransformer | ONNX | float | Snapdragon® 8 Elite Mobile | 236.364 ms | 168 - 5681 MB | NPU | StateTransformer | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 212.445 ms | 183 - 5749 MB | NPU | StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1528.046 ms | 294 - 816 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1115.87 ms | 241 - 394 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® SA8650P | 792.928 ms | 452 - 465 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® SA8255P | 792.928 ms | 452 - 465 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® QCS8450 | 808.833 ms | 450 - 470 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1309.723 ms | 293 - 815 MB | CPU | StateTransformer | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 645.781 ms | 267 - 4157 MB | CPU | StateTransformer | TFLITE | float | Snapdragon® 8 Elite Mobile | 645.781 ms | 267 - 4157 MB | CPU ## License * The license for the original implementation of StateTransformer can be found [here](https://github.com/Tsinghua-MARS-Lab/StateTransformer/blob/main/setup.py). ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).