[GH-ISSUE #19211] issue:

GiteaMirror commented

2026-04-20 01:02:14 -05:00

Owner

Originally created by @Byrnes9 on GitHub (Nov 16, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/19211

Check Existing Issues

I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

0.6.36

Ollama Version (if applicable)

0.12.11

Operating System

Ubuntu server, 22.04

Browser (if applicable)

Vivaldi

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

I'm trying to get my LLM's to respond to multiple prompts in the same chat.

Actual Behavior

After my first prompt, webui stops responding or slows down considerably, when I check ollama ps I get this:
qwen3:30b ad815644918f 19 GB 100% CPU 4096 ...Stopping

Steps to Reproduce

start the service
input first prompt
wait for response
input second prompt
stops responding

Logs & Screenshots

Docker log attached:

docker log.docx

Additional Information

I am running ollama on cpu only with 64gb of RAM

Originally created by @Byrnes9 on GitHub (Nov 16, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/19211 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version 0.6.36 ### Ollama Version (if applicable) 0.12.11 ### Operating System Ubuntu server, 22.04 ### Browser (if applicable) Vivaldi ### 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 **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] 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). - [x] 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 I'm trying to get my LLM's to respond to multiple prompts in the same chat. ### Actual Behavior After my first prompt, webui stops responding or slows down considerably, when I check ollama ps I get this: qwen3:30b ad815644918f 19 GB 100% CPU 4096 ...Stopping ### Steps to Reproduce 1. start the service 2. input first prompt 3. wait for response 4. input second prompt 5. stops responding ### Logs & Screenshots Docker log attached: [docker log.docx](https://github.com/user-attachments/files/23568892/docker.log.docx) ### Additional Information I am running ollama on cpu only with 64gb of RAM