The Data Center provides an AI service for JGU. This includes various large language models. The ZDV controls and hosts the service itself, so the data (except for the web search) remains within JGU.
Log in
You will need a JGU account to log in. The AI chat is initially available to employees. The offer for students is currently being prepared.
Log in at https://ki-chat.uni-mainz.de with the login details of your JGU account.
Available AI Models
Model updates each semester
In future, it is planned to update the models once per semester. Where possible, this will take place during the lecture-free period and will be announced in advance.
- The model updates will not result in any fundamental changes for users. The models will become more powerful, more reliable, and of higher quality.
- In addition, the AI chat user interface (OpenWebUI) can also be updated and enhanced with new features during breaks between semesters.
- Predefined prompts that have already been created can normally continue to be used.
Current models
| AI Model | Description | Origin/Level of Knowlege | Usage |
| DeepSeek V4.1 Flash |
Efficient multimodal mixture-of-experts model with approximately 763 billion parameters and adjustable reasoning* Official documentation: |
DeepSeek, Release 09/2026, Level of knowledge not published |
General chat application, complex and agent-based tasks, coding, creating and summarizing text, image and document analysis |
| Qwen3.6 35B | Official documentation and manufacturer Benchmarks: https://huggingface.co/Qwen/Qwen3.6-35B-A3B Quantization used: https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8 |
Alibaba Cloud, Release 04/2026, Level of knowledge not published |
General chat application, coding, creating and summarizing text |
*Refers to the ability of the model to create an internal monologue to give more precise or logical answers.
Image models
| Model | Description | Usage |
| Z-Image-Turbo |
Optimized version of the Z-Image image creation model Official documentation: |
Creating images |
| Qwen-Image-Edit-2511 Lightning Variante | Optimized version of Qwen-Image-Edit-2511Official documentation: https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning |
Editing Images |
System Components
- Frontend (OpenWebUI): User interface for interaction.
- Load balancer (LiteLLM): Central interface to AI server(s).
- AI server (vllm): Executes the AI models on the GPUs.
Overview of Functions and Applications
News and Plans
All Posts and News combined: https://www.en-zdv.uni-mainz.de/tag/ai/
We are currently working on the following projects:
- Enabling additional features for the AI chat user interface (OpenWebUI)
- Tool-calling integrations (e.g., search in arXiv)
Overview of Frequently Asked Questions (FAQ)
- How long can I save Chats?
- How can I share and export Chats?
- How can I upload Files and what do I need to consider?
- How does voice-based interaction (voice input and audio processing) work?
How do I optomize my Results?
For optimal results, please formulate your query in English. English is clearly dominant in the training data for all AI models.
Data protection
Where is my data processed?
All components of the system are hosted and operated by the ZDV of Johannes Gutenberg University Mainz. The JGU AI Chat runs as a local model on JGU servers, which means that as a general rule all data remains on ZDV servers and is not transmitted to external third parties.
The only exception is necessarily the web search function. When web search is enabled, your prompt is enriched with additional information, for example the current date. Where required, the prompt is sent in summarised form to our search provider Tavily (https://www.tavily.com/) in order to answer the search query. The prompt is subsequently discarded in accordance with the contract and configuration. As a matter of principle, no files or images are transmitted. In some cases, however, the model that generates the search query may draw on relevant information from the context in order to enrich the query.
In particular when web search is enabled, do not enter any personal or confidential information unless it is required for the search.
Personal data
The processing of personal data in the AI Chat is generally permissible provided that the applicable data protection requirements are met. The term “personal data” refers, within the meaning of Art. 4(1) GDPR, to all information relating to an identified or identifiable natural person. Personal data should only be processed where this is necessary for the respective request.
In many cases, the use of personal data in the AI Chat is not necessary and can be dispensed with without any loss in the quality of the result. Instead of “Evaluate the email from Max Mustermann, Head of the Institute of Example Sciences, to Ms Erika Beispiel …”, you could for example write: “Evaluate the following email from an institute director …”. Processing without any personal reference is generally to be preferred.
Refraining from personal data is equivalent to using anonymised data. In this case, personal data is modified in such a way that the data subject can no longer be identified. As anonymised data has no personal reference, the GDPR does not apply to such data.
Where a personal reference is necessary for processing, pseudonymisation should be used in order to protect the personal data of the data subjects. Under Art. 4(5) GDPR, pseudonymisation means the processing of personal data in such a way that the data can no longer be attributed to a specific person without the use of additional information. This additional information must be kept separately and protected by appropriate technical and organisational measures. Pseudonymised data nevertheless remains personal data and continues to be subject to the GDPR.
Principle for use
Only process personal data in the AI Chat that is actually necessary for your request. Remove or anonymise personal references if they are not needed for the desired result.
Support
Members of the University of Mainz with application questions please contact the Digital Teaching Competence Team.
Email: digitale-lehre@uni-mainz.de
Members of the University of Mainz with technical questions please contact the unix group of ZDV.
Email: unix@uni-mainz.de