I have searched for all existing open AND closed issues and discussions for similar requests. I have found none that is comparable to my request.
Verify Feature Scope
I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.
Problem Description
When a new model is installed, the back-end model area shows it and is able to be eddied but to have it on the font page to use it, a restart is needed.
Desired Solution you'd like
Auto reloads model information from ollama.
Alternatives Considered
No response
Additional Context
No response
Originally created by @Hello-World-Traveler on GitHub (Dec 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20217
### Check Existing Issues
- [x] I have searched for all existing **open AND closed** issues and discussions for similar requests. I have found none that is comparable to my request.
### Verify Feature Scope
- [x] I have read through and understood the scope definition for feature requests in the Issues section. I believe my feature request meets the definition and belongs in the Issues section instead of the Discussions.
### Problem Description
When a new model is installed, the back-end model area shows it and is able to be eddied but to have it on the font page to use it, a restart is needed.
### Desired Solution you'd like
Auto reloads model information from ollama.
### Alternatives Considered
_No response_
### Additional Context
_No response_
@owui-terminator[bot] commented on GitHub (Dec 28, 2025):
🔍Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#606feat: Load new models for model picker instead of caching by chrishart0 • Jan 31, 2024
#19319feat: Add option for OpenWebui to use the context length of a currently loaded model in Ollama to keep the model from being reloaded. by hainesk • Nov 20, 2025
#1726way to pull already pulled models to get updates by TadayukiOkada • Apr 24, 2024
#16312feat: Fetch model list in background thread by dattasid • Aug 06, 2025
#670 **feat: usage of new keep_alive parameter in ollama ** by nick-tonjum • Feb 07, 2024
Show 5 more related issues
#9507Model List in Open Web UI Not Updating After Removal of a model from Ollama by Mr-K-AB • Feb 06, 2025
#3987Preload Ollama models upon user login by knguyen298 • Jul 18, 2024
#8036ollama instant load all by Rifl33 • Dec 24, 2024
#3754Feature: Show if a model is updatable by lirc571 • Jul 10, 2024
#19033feat: Same search and hover for true model name for LLM Selection for Models in Workspace by Wladastic • Nov 08, 2025
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3694485190 -->
@owui-terminator[bot] commented on GitHub (Dec 28, 2025):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#606](https://github.com/open-webui/open-webui/issues/606) **feat: Load new models for model picker instead of caching**
*by chrishart0 • Jan 31, 2024*
2. [#19319](https://github.com/open-webui/open-webui/issues/19319) **feat: Add option for OpenWebui to use the context length of a currently loaded model in Ollama to keep the model from being reloaded.**
*by hainesk • Nov 20, 2025*
3. [#1726](https://github.com/open-webui/open-webui/issues/1726) **way to pull already pulled models to get updates**
*by TadayukiOkada • Apr 24, 2024*
4. [#16312](https://github.com/open-webui/open-webui/issues/16312) **feat: Fetch model list in background thread**
*by dattasid • Aug 06, 2025*
5. [#670](https://github.com/open-webui/open-webui/issues/670) **feat: usage of new keep_alive parameter in ollama **
*by nick-tonjum • Feb 07, 2024*
<details>
<summary>Show 5 more related issues</summary>
6. [#9507](https://github.com/open-webui/open-webui/issues/9507) **Model List in Open Web UI Not Updating After Removal of a model from Ollama**
*by Mr-K-AB • Feb 06, 2025*
7. [#3987](https://github.com/open-webui/open-webui/issues/3987) **Preload Ollama models upon user login**
*by knguyen298 • Jul 18, 2024*
8. [#8036](https://github.com/open-webui/open-webui/issues/8036) **ollama instant load all**
*by Rifl33 • Dec 24, 2024*
9. [#3754](https://github.com/open-webui/open-webui/issues/3754) **Feature: Show if a model is updatable**
*by lirc571 • Jul 10, 2024*
10. [#19033](https://github.com/open-webui/open-webui/issues/19033) **feat: Same search and hover for true model name for LLM Selection for Models in Workspace**
*by Wladastic • Nov 08, 2025*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
do you use model caching? there are two env vars and also toggles in the UI that cache the model list and prevent auto model fetching.
<!-- gh-comment-id:3696348705 -->
@Classic298 commented on GitHub (Dec 29, 2025):
do you use model caching? there are two env vars and also toggles in the UI that cache the model list and prevent auto model fetching.
@Hello-World-Traveler commented on GitHub (Dec 29, 2025):
I don't think I have model caching enabled unless it's abled by default.
<!-- gh-comment-id:3697517068 -->
@Hello-World-Traveler commented on GitHub (Dec 29, 2025):
I don't think I have model caching enabled unless it's abled by default.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Hello-World-Traveler on GitHub (Dec 28, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/20217
Check Existing Issues
Verify Feature Scope
Problem Description
When a new model is installed, the back-end model area shows it and is able to be eddied but to have it on the font page to use it, a restart is needed.
Desired Solution you'd like
Auto reloads model information from ollama.
Alternatives Considered
No response
Additional Context
No response
@owui-terminator[bot] commented on GitHub (Dec 28, 2025):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#606 feat: Load new models for model picker instead of caching
by chrishart0 • Jan 31, 2024
#19319 feat: Add option for OpenWebui to use the context length of a currently loaded model in Ollama to keep the model from being reloaded.
by hainesk • Nov 20, 2025
#1726 way to pull already pulled models to get updates
by TadayukiOkada • Apr 24, 2024
#16312 feat: Fetch model list in background thread
by dattasid • Aug 06, 2025
#670 **feat: usage of new keep_alive parameter in ollama **
by nick-tonjum • Feb 07, 2024
Show 5 more related issues
#9507 Model List in Open Web UI Not Updating After Removal of a model from Ollama
by Mr-K-AB • Feb 06, 2025
#3987 Preload Ollama models upon user login
by knguyen298 • Jul 18, 2024
#8036 ollama instant load all
by Rifl33 • Dec 24, 2024
#3754 Feature: Show if a model is updatable
by lirc571 • Jul 10, 2024
#19033 feat: Same search and hover for true model name for LLM Selection for Models in Workspace
by Wladastic • Nov 08, 2025
💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@Classic298 commented on GitHub (Dec 29, 2025):
do you use model caching? there are two env vars and also toggles in the UI that cache the model list and prevent auto model fetching.
@Hello-World-Traveler commented on GitHub (Dec 29, 2025):
I don't think I have model caching enabled unless it's abled by default.