[GH-ISSUE #11704] feat: How can the same Ollama model appear multiple times in the model list with different system prompts? #70928

New Issue

GiteaMirror · 2026-05-13T02:54:48-05:00

GiteaMirror commented

2026-05-13 02:54:48 -05:00

Originally created by @yelluo on GitHub (Mar 15, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/11704

Check Existing Issues

I have searched the existing issues and discussions.

Problem Description

It is not possible to have the same OLLAMA model appear multiple times in the model list with different system prompts.

Desired Solution you'd like

After adding a model, you can modify its display name, but you cannot duplicate the model. When setting up connections, you can add the same model repeatedly, but the model list page only displays one instance. Exporting the model list to a JSON file and then modifying it to add the same model with different names does not result in seeing two models in the model list after importing the JSON.
The same Ollama model is not reloaded on the server side, which reduces memory usage and improves response speed; different system prompts or model parameter settings can be used to achieve various functions.
You can set advanced chat parameters to allow the same model to have different system prompts. However, it is hoped that administrators will set this up in advance so that other users can directly select a model from the model list to achieve specific functions.

Alternatives Considered

No response

Additional Context

No response

Originally created by @yelluo on GitHub (Mar 15, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/11704 ### Check Existing Issues - [x] I have searched the existing issues and discussions. ### Problem Description It is not possible to have the same OLLAMA model appear multiple times in the model list with different system prompts. ### Desired Solution you'd like After adding a model, you can modify its display name, but you cannot duplicate the model. When setting up connections, you can add the same model repeatedly, but the model list page only displays one instance. Exporting the model list to a JSON file and then modifying it to add the same model with different names does not result in seeing two models in the model list after importing the JSON. The same Ollama model is not reloaded on the server side, which reduces memory usage and improves response speed; different system prompts or model parameter settings can be used to achieve various functions. You can set advanced chat parameters to allow the same model to have different system prompts. However, it is hoped that administrators will set this up in advance so that other users can directly select a model from the model list to achieve specific functions. ### Alternatives Considered _No response_ ### Additional Context _No response_

GiteaMirror closed this issue

2026-05-13 02:54:49 -05:00

GiteaMirror commented

2026-05-13 02:54:50 -05:00

@Classic298 commented on GitHub (Mar 15, 2025):

I think what you want to do is go to the workspace and create a few custom models with different system prompts but the same base model. These will then display seperately.

@Classic298 commented on GitHub (Mar 15, 2025): I think what you want to do is go to the workspace and create a few custom models with different system prompts but the same base model. These will then display seperately.

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#70928