[GH-ISSUE #16306] release new version with bundled ollama 0.11 to support gpt-oss models #33386

Closed
opened 2026-04-25 07:17:30 -05:00 by GiteaMirror · 7 comments
Owner

Originally created by @sbe-arg on GitHub (Aug 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/16306

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

0.6.18

Ollama Version (if applicable)

No response

Operating System

fedora

Browser (if applicable)

No response

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

Current version of ollama needs updating to support gpt-oss

https://ollama.com/library/gpt-oss

Actual Behavior

n/a

Steps to Reproduce

n/a

Logs & Screenshots

n/a

Additional Information

n/a

Originally created by @sbe-arg on GitHub (Aug 5, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/16306 ### 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 0.6.18 ### Ollama Version (if applicable) _No response_ ### Operating System fedora ### Browser (if applicable) _No response_ ### 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 Current version of ollama needs updating to support gpt-oss https://ollama.com/library/gpt-oss ### Actual Behavior n/a ### Steps to Reproduce n/a ### Logs & Screenshots n/a ### Additional Information n/a
GiteaMirror added the bug label 2026-04-25 07:17:30 -05:00
Author
Owner

@sbe-arg commented on GitHub (Aug 5, 2025):

FYI in the meantime I'm just updating ollama on container start doing XD

  open-webui:
    image: ghcr.io/open-webui/open-webui:ollama
    container_name: open-webui
    restart: always
    ports:
      - "3000:8080"
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
      - open-webui_data:/app/backend/data
    environment:
      - OLLAMA_HOST=0.0.0.0
    command: >
      sh -c "curl -fsSL https://ollama.com/install.sh | sh && exec bash start.sh"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
<!-- gh-comment-id:3156701125 --> @sbe-arg commented on GitHub (Aug 5, 2025): FYI in the meantime I'm just updating ollama on container start doing XD ``` open-webui: image: ghcr.io/open-webui/open-webui:ollama container_name: open-webui restart: always ports: - "3000:8080" - "11434:11434" volumes: - ollama_data:/root/.ollama - open-webui_data:/app/backend/data environment: - OLLAMA_HOST=0.0.0.0 command: > sh -c "curl -fsSL https://ollama.com/install.sh | sh && exec bash start.sh" deploy: resources: reservations: devices: - driver: nvidia count: all capabilities: [gpu] ```
Author
Owner

@rgaricano commented on GitHub (Aug 6, 2025):

some issues for this model fixed in ollama v0.11.2 and more in pre-release v0.11.3

<!-- gh-comment-id:3158357345 --> @rgaricano commented on GitHub (Aug 6, 2025): some issues for this model fixed in ollama [v0.11.2](https://github.com/ollama/ollama/releases/tag/v0.11.2) and more in pre-release [v0.11.3](https://github.com/ollama/ollama/releases/tag/v0.11.3)
Author
Owner

@gaby commented on GitHub (Aug 7, 2025):

v0.11.3 has been released

<!-- gh-comment-id:3162102810 --> @gaby commented on GitHub (Aug 7, 2025): v0.11.3 has been released
Author
Owner

@marabgol commented on GitHub (Aug 7, 2025):

the issue 'issue:500 : template' is resolved , thanks

<!-- gh-comment-id:3162120893 --> @marabgol commented on GitHub (Aug 7, 2025): the issue 'issue:500 : template' is resolved , thanks
Author
Owner

@gaby commented on GitHub (Aug 7, 2025):

This is only resolved if installing stuff manually. The latest docker image from OpenWebUI has the same bug

<!-- gh-comment-id:3162123876 --> @gaby commented on GitHub (Aug 7, 2025): This is only resolved if installing stuff manually. The latest docker image from OpenWebUI has the same bug
Author
Owner

@gaby commented on GitHub (Aug 9, 2025):

This can be closed, release was done today

<!-- gh-comment-id:3172195824 --> @gaby commented on GitHub (Aug 9, 2025): This can be closed, release was done today
Author
Owner

@Werewolfke commented on GitHub (Aug 10, 2025):

Image

Version v0.6.21 still not working to pull gpt-oss
Docker webui and ollama together, cpu only.

<!-- gh-comment-id:3172758830 --> @Werewolfke commented on GitHub (Aug 10, 2025): <img width="386" height="282" alt="Image" src="https://github.com/user-attachments/assets/510801e8-9746-4876-a91b-bbd52eeef1ec" /> Version v0.6.21 still not working to pull gpt-oss Docker webui and ollama together, cpu only.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#33386