github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13720] Cannot Upgrade Ollama on Windows 11 — Server Version Stuck at 0.11.0 Despite Client Update #71054

New Issue
Closed
opened 2026-05-04 23:51:38 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-04 23:51:38 -05:00
Owner
Copy Link

Originally created by @gismc123 on GitHub (Jan 14, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13720

What is the issue?

System Info:

  • OS: Windows 11
  • RAM: 32GB DDR4
  • GPU: NVIDIA RTX 3060
  • Ollama Client Installed Version: 0.14.0
  • Ollama Server/Daemon Version: 0.11.0
  • Issue: Cannot pull models like gpt-oss:20b due to version mismatch

Description:
After multiple attempts, I am unable to get the Ollama server/daemon to upgrade on my Windows 11 PC. Although I can install the latest client (0.14.0), the server remains at 0.11.0. This prevents me from pulling certain models, such as gpt-oss:20b, with the following error:

pulling manifest
Error: pull model manifest: 412:
The model you are attempting to pull requires a newer version of Ollama.

Troubleshooting Steps Taken:

  1. Verified versions:
ollama --version

Output:

ollama version is 0.11.0
Warning: client version is 0.14.0

  1. Uninstalled Ollama via Windows “Apps & Features” → confirmed uninstall.

  2. Deleted Ollama folders manually:

  • C:\Users\--username--\AppData\Local\Programs\Ollama
  • C:\Users\--username--\.ollama

  1. Attempted deletions from Safe Mode and Windows Recovery Environment (WinRE) Command Prompt — deletion succeeded in both environments.

  2. Reinstalled Ollama fresh from https://ollama.com/download.

  3. After reinstall and restart, the version mismatch persists: server 0.11.0, client 0.14.0.

Observations:

  • The mismatch persists even after completely removing all known Ollama folders and reinstalling.

Goal:

  • Fully upgrade the Ollama server/daemon to match client version 0.14.0.
  • Successfully pull models like gpt-oss:20b.

Request:

  • Guidance on how to completely remove any hidden or locked Ollama server components on Windows 11.
  • Steps to ensure that after reinstall, the Ollama server/daemon version matches the latest client.

Relevant log output

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.11.0

Originally created by @gismc123 on GitHub (Jan 14, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13720 ### What is the issue? **System Info:** * OS: Windows 11 * RAM: 32GB DDR4 * GPU: NVIDIA RTX 3060 * Ollama Client Installed Version: 0.14.0 * Ollama Server/Daemon Version: 0.11.0 * Issue: Cannot pull models like `gpt-oss:20b` due to version mismatch **Description:** After multiple attempts, I am unable to get the Ollama server/daemon to upgrade on my Windows 11 PC. Although I can install the latest client (0.14.0), the server remains at 0.11.0. This prevents me from pulling certain models, such as `gpt-oss:20b`, with the following error: ``` pulling manifest Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama. ``` **Troubleshooting Steps Taken:** 1. Verified versions: ```powershell ollama --version ``` Output: ``` ollama version is 0.11.0 Warning: client version is 0.14.0 ``` 2. Uninstalled Ollama via Windows “Apps & Features” → confirmed uninstall. 3. Deleted Ollama folders manually: * `C:\Users\--username--\AppData\Local\Programs\Ollama` * `C:\Users\--username--\.ollama` 4. Attempted deletions from **Safe Mode** and **Windows Recovery Environment (WinRE)** Command Prompt — deletion succeeded in both environments. 5. Reinstalled Ollama fresh from [https://ollama.com/download](https://ollama.com/download). 6. After reinstall and restart, the version mismatch persists: server 0.11.0, client 0.14.0. **Observations:** * The mismatch persists even after completely removing all known Ollama folders and reinstalling. **Goal:** * Fully upgrade the Ollama server/daemon to match client version 0.14.0. * Successfully pull models like `gpt-oss:20b`. **Request:** * Guidance on how to completely remove any hidden or locked Ollama server components on Windows 11. * Steps to ensure that after reinstall, the Ollama server/daemon version matches the latest client. ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.11.0
GiteaMirror added the bug label 2026-05-04 23:51:38 -05:00
GiteaMirror commented 2026-05-04 23:51:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 15, 2026):

Have you previously installed ollama in WSL?

<!-- gh-comment-id:3753042780 --> @rick-github commented on GitHub (Jan 15, 2026): Have you previously installed ollama in WSL?
GiteaMirror commented 2026-05-04 23:51:49 -05:00
Author
Owner
Copy Link

@gismc123 commented on GitHub (Jan 15, 2026):

Have you previously installed ollama in WSL?

Its possible I have. But do not remember. How do i check?

<!-- gh-comment-id:3756567492 --> @gismc123 commented on GitHub (Jan 15, 2026): > Have you previously installed ollama in WSL? Its possible I have. But do not remember. How do i check?
GiteaMirror commented 2026-05-04 23:51:49 -05:00
Author
Owner
Copy Link

@gismc123 commented on GitHub (Jan 15, 2026):

✅ Resolution – Root Cause Was Ollama Running Inside WSL (Ubuntu)

Thank you so much for the direction. I googled how to check WSL and found my response. I can't believe how stupid I feel after spending hours on this issue and almost considering nuking my OS and reinstalling Windows.

The problem was not the Windows install itself — I had an older Ollama installation running inside WSL (Ubuntu), and the Windows client was connecting to that daemon instead of the native Windows service.

How I solved it:

  1. Opened PowerShell.

  2. Started a WSL Ubuntu session.

  3. In the Ubuntu terminal, ran:

    ollama -v

  4. Output showed:

    ollama version 0.11.0

    This confirmed that an outdated Ollama daemon was running inside WSL.

How I fixed it (inside Ubuntu / WSL):

sudo systemctl stop ollama
sudo systemctl disable ollama
sudo rm $(which ollama)
sudo rm -r /usr/share/ollama
sudo userdel ollama

After removing Ollama from WSL and restarting, the Windows Ollama installation correctly reported the newer version and the client/server version mismatch was resolved. I am now able to pull models successfully.

Closing this issue. ✅

<!-- gh-comment-id:3756796134 --> @gismc123 commented on GitHub (Jan 15, 2026): ### ✅ Resolution – Root Cause Was Ollama Running Inside WSL (Ubuntu) Thank you so much for the direction. I googled how to check WSL and found my response. I can't believe how stupid I feel after spending hours on this issue and almost considering nuking my OS and reinstalling Windows. The problem was not the Windows install itself — I had an older Ollama installation running inside WSL (Ubuntu), and the Windows client was connecting to that daemon instead of the native Windows service. **How I solved it:** 1. Opened PowerShell. 2. Started a WSL Ubuntu session. 3. In the Ubuntu terminal, ran: ``` ollama -v ``` 4. Output showed: ``` ollama version 0.11.0 ``` This confirmed that an outdated Ollama daemon was running inside WSL. **How I fixed it (inside Ubuntu / WSL):** ``` sudo systemctl stop ollama sudo systemctl disable ollama sudo rm $(which ollama) sudo rm -r /usr/share/ollama sudo userdel ollama ``` After removing Ollama from WSL and restarting, the Windows Ollama installation correctly reported the newer version and the client/server version mismatch was resolved. I am now able to pull models successfully. Closing this issue. ✅
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#71054
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?