Last updated: April 2026
MiniCPM-V Demo ("the App") is an on-device multimodal large language model demonstration application. The App performs all AI inference locally on your device. We do not collect, store, or transmit any personal data to our servers.
We do not collect any personal data. The App does not contain any analytics SDK, advertising SDK, or third-party data collection tool.
All image, audio, and text inputs you provide are processed entirely on your device. None of this data is transmitted to our servers or any third party.
The App requests the following device permissions, all used strictly for local functionality:
- Camera: to capture images for on-device analysis.
- Photo Library: to select images for on-device analysis.
- Microphone: to record audio for on-device speech recognition.
- Speech Recognition: to convert speech to text locally.
- Local Network: to download model weights from public model repositories (e.g., Hugging Face, ModelScope). No personal data is transmitted.
You may revoke any of these permissions at any time in iOS Settings. The App may have reduced functionality without them.
The App downloads model weight files from publicly accessible URLs such as Hugging Face and ModelScope. Downloading these files follows the privacy practices of those services. We do not log or record which models you download.
All model files and user-generated content remain in the App's sandboxed Documents directory on your device. Uninstalling the App removes all local data.
The App is not directed to children under 13. We do not knowingly collect information from anyone, including children.
We may update this policy from time to time. Any changes will be published on this page with an updated date.
For questions about this policy, please open an issue at: https://github.com/OpenBMB/MiniCPM-V-Apps/issues