> For the complete documentation index, see [llms.txt](https://unsloth.ai/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://unsloth.ai/docs/de/neu.md).

# Neu

- [Unsloth-Updates](https://unsloth.ai/docs/de/neu/changelog.md): Unsloth-Changelog für unsere neuesten Releases, Verbesserungen und Fixes.
- [Unsloth Studio vorgestellt](https://unsloth.ai/docs/de/neu/studio.md): KI-Modelle lokal mit Unsloth Studio ausführen und trainieren.
- [Erste Schritte mit Unsloth Studio](https://unsloth.ai/docs/de/neu/studio/start.md): Ein Leitfaden für den Einstieg in das Fine-Tuning-Studio, Datenrezepte, das Exportieren von Modellen und den Chat.
- [Wie man Modelle mit Unsloth ausführt](https://unsloth.ai/docs/de/neu/studio/chat.md): KI-Modelle, LLMs und GGUFs lokal mit Unsloth Studio ausführen.
- [Unsloth Studio Installation](https://unsloth.ai/docs/de/neu/studio/install.md): Installiere Unsloth Studio manuell oder lade die separate Unsloth Desktop-App herunter.
- [Unsloth-Datenrezepte](https://unsloth.ai/docs/de/neu/studio/data-recipe.md): Erfahre, wie du Datensätze mit den Datenrezepten von Unsloth Studio erstellst, aufbaust und bearbeitest.
- [Modelle mit Unsloth Studio exportieren](https://unsloth.ai/docs/de/neu/studio/export.md): Erfahre, wie du deine Safetensor- oder LoRA-Modelldateien in GGUF oder andere Formate exportierst.
- [Sicherheit in Unsloth](https://unsloth.ai/docs/de/neu/studio/security.md)
- [Sandboxing in Unsloth](https://unsloth.ai/docs/de/neu/studio/sandboxing-in-unsloth.md): Unsloth verwendet unter Linux bubblewrap, unter macOS Seatbelt und unter Windows MXC.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://unsloth.ai/docs/de/neu.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.