Support intro
Sorry to hear you’re facing problems. 
The community help forum (help.nextcloud.com) is for home and non-enterprise users. Support is provided by other community members on a best effort / “as available” basis. All of those responding are volunteering their time to help you.
If you’re using Nextcloud in a business/critical setting, paid and SLA-based support services can be accessed via portal.nextcloud.com where Nextcloud engineers can help ensure your business keeps running smoothly.
Getting help
In order to help you as efficiently (and quickly!) as possible, please fill in as much of the below requested information as you can.
Before clicking submit: Please check if your query is already addressed via the following resources:
- Official documentation (searchable and regularly updated)
- How to topics and FAQs
- Forum search
(Utilizing these existing resources is typically faster. It also helps reduce the load on our generous volunteers while elevating the signal to noise ratio of the forums otherwise arising from the same queries being posted repeatedly).
The Basics
- Nextcloud Server version (e.g., 29.x.x):
- Nextcloud Hub 10 - 31.0.4 - AIO
- Operating system and version (e.g., Ubuntu 24.04):
- openSUSE
- Installation method (e.g. AlO, NCP, Bare Metal/Archive, etc.)
- AIO
- Are you using CloudfIare, mod_security, or similar? (Yes / No)
- nope
Summary of the issue you are facing:
I’m having trouble to get the Nextcloud Assistant perform sensible tasks, even after trying a variety of models. I understand that the model has to provide tool calling functionalities, but even with those models my Assistant only want’s to perform bogus tasks, e.g. create an calendar entry and not retrieving the correct mail address… Mistral 7b was not capable of funcion calling if I understand correctly. Currently I am running Gemma 3 4B, and that works well in general. It is however also still very off when creating calendar entries and wants to perform bogus tasks.
Context Agent is version 1.1.0.
Do you have suggestions for models (in maximum the 7-8b range, for more my GPU it not sufficient 
) that work well with the assistant? If you could even share your setup, especially if you managed to get those models to work within LocalAI, I would be more than happy.
At least for now…