I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
v0.6.9
Ollama Version (if applicable)
0.6.8 (but likely not applicable)
Operating System
Fedora 43
Browser (if applicable)
Chromium 136.0.7103.92
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
The Web UI part should not use that much CPU and RAM.
Actual Behavior
While generating an answer (on a remote OLLAMA) the browser consumes 100% of one CPU core (I suspect that it could have consumed more but it is limited by the single thread of Javascript).
After a while (1-10 minutes) the RAM consumption becomes quite high which is not a thing I expect.
It impossible to get any response as the browser is essentially freezes after 1 minute of executing (rendering) response from an ML model.
In addition to that, it is unclear to me why /api/models request returns UUIDs of all the files in knowledge base. With the number of files in my knowledge base about 60000+, it makes the response about ~43-50MB which is a lot, if one wants to use the Open WebUI via mobile connection and a lot to Parse at the client browser side.
Adding /nothink to the prompt or system prompt (to force the QWEN model to disable thinking mode and immediately generate response) somewhat reduces load but the Web UI is still slow-ish.
Originally created by @ErmakovDmitriy on GitHub (May 13, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13831
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
v0.6.9
### Ollama Version (if applicable)
0.6.8 (but likely not applicable)
### Operating System
Fedora 43
### Browser (if applicable)
Chromium 136.0.7103.92
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
The Web UI part should not use that much CPU and RAM.
### Actual Behavior
While generating an answer (on a remote OLLAMA) the browser consumes 100% of one CPU core (I suspect that it could have consumed more but it is limited by the single thread of Javascript).
After a while (1-10 minutes) the RAM consumption becomes quite high which is not a thing I expect.
It impossible to get any response as the browser is essentially freezes after 1 minute of executing (rendering) response from an ML model.
In addition to that, it is unclear to me why `/api/models` request returns UUIDs of all the files in knowledge base. With the number of files in my knowledge base about 60000+, it makes the response about ~43-50MB which is a lot, if one wants to use the Open WebUI via mobile connection and a lot to Parse at the client browser side.
### Steps to Reproduce
1. Open a browser with the only tab with Open WebUI.
2. Open new chat with QWEN3 ("thinking") model.
3. Run any request.
4. Wait until browser freezes.
5. Reproducible both in Chromium and Firefox 138.
### Logs & Screenshots
[chromium-console.log](https://github.com/user-attachments/files/20182378/chromium-console.log)
No errors, warnings in server log.
### Additional Information
Adding `/nothink` to the prompt or system prompt (to force the QWEN model to disable `thinking` mode and immediately generate response) somewhat reduces load but the Web UI is still slow-ish.
GiteaMirror
added the bug label 2026-04-19 22:49:17 -05:00
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 @ErmakovDmitriy on GitHub (May 13, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/13831
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.9
Ollama Version (if applicable)
0.6.8 (but likely not applicable)
Operating System
Fedora 43
Browser (if applicable)
Chromium 136.0.7103.92
Confirmation
README.md.Expected Behavior
The Web UI part should not use that much CPU and RAM.
Actual Behavior
While generating an answer (on a remote OLLAMA) the browser consumes 100% of one CPU core (I suspect that it could have consumed more but it is limited by the single thread of Javascript).
After a while (1-10 minutes) the RAM consumption becomes quite high which is not a thing I expect.
It impossible to get any response as the browser is essentially freezes after 1 minute of executing (rendering) response from an ML model.
In addition to that, it is unclear to me why
/api/modelsrequest returns UUIDs of all the files in knowledge base. With the number of files in my knowledge base about 60000+, it makes the response about ~43-50MB which is a lot, if one wants to use the Open WebUI via mobile connection and a lot to Parse at the client browser side.Steps to Reproduce
Logs & Screenshots
chromium-console.log
No errors, warnings in server log.
Additional Information
Adding
/nothinkto the prompt or system prompt (to force the QWEN model to disablethinkingmode and immediately generate response) somewhat reduces load but the Web UI is still slow-ish.