Originally created by @skjoedt on GitHub (Jul 7, 2025).
Check Existing Issues
I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
v0.6.15
Ollama Version (if applicable)
N/A
Operating System
MacOS and Ubuntu 22.04
Browser (if applicable)
Chrome 138.0.7204.93
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 provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
A non-admin user should see the same page loading time for openwebui as an admin user.
Actual Behavior
A non-admin user with access to 5 models has page loading times (specific to the models api request) at 10x an admin user with access to all models.
In testing (localhost); 950 ms vs 150 ms
In production; 3500 ms vs 350 ms
Steps to Reproduce
On localhost running MacOS 15.5 (Macbook M1)
Run latest docker version using orbstack
Deploy webui with the docker compose file below
Deploy litellm with the config.yaml below having all 6 external AI apis with wildcards to select all available models
Refresh page of http://chat.traefik.me with the admin user and see network requests to chat.traefik.me/api/models api at around 150 ms (around 350 ms in production)
Refresh page of http://chat.traefik.me with a non-admin user and see network requests to the chat.traefik.me/api/models api at around 950 ms (worse in production with times around 3.5 s)
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 @skjoedt on GitHub (Jul 7, 2025).
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.15
Ollama Version (if applicable)
N/A
Operating System
MacOS and Ubuntu 22.04
Browser (if applicable)
Chrome 138.0.7204.93
Confirmation
README.md.Expected Behavior
A non-admin user should see the same page loading time for openwebui as an admin user.
Actual Behavior
A non-admin user with access to 5 models has page loading times (specific to the models api request) at 10x an admin user with access to all models.
In testing (localhost); 950 ms vs 150 ms
In production; 3500 ms vs 350 ms
Steps to Reproduce
Docker compose (excluding litellm deployment)
Litellm config to show number of available models exposed to openwebui
Logs & Screenshots
Chrome console log
And snippet from network log showing models takes 3.4 seconds to load.
Docker container logs
Additional Information
No response
@tjbck commented on GitHub (Jul 7, 2025):
Unable to reproduce from our end, keep us updated!