github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13266] Pulling a model changes server version information? #34528

New Issue
Closed
opened 2026-04-22 18:10:52 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 18:10:52 -05:00
Owner
Copy Link

Originally created by @AMueckl on GitHub (Nov 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13266

What is the issue?

After having uninstalled Ollama, wiped-off all residual windows registry entries, rebooted Windows, re-installed Ollama using OllamaSetup.exe, downloaded from github Release 0.13.0, I tried to pull gpt-oss:latest.

The output below is the console output after the installation was completed.

It can be seen that:

  • ollama -v shows version 0.13.0
  • ollama pull gpt-oss:latest stops after approx. 140MB
  • a retry of ollama pull gpt-oss:latest yielded: "Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama."
  • ollama -v then shows a different version 0.4.6, while the client version still is at 0.13.0

Note:
The steps observed happend within 1-2 minutes, there had not been any other interactions with the computer.

Relevant log output

Working Console output:
PS C:\Users\me> ollama -v
ollama version is 0.13.0
PS C:\Users\me> ollama pull gpt-oss:latest
pulling manifest
pulling e7b273f96360:   1% ▕                                                          ▏ 140 MB/ 13 GB  6.3 MB/s  36m21s
PS C:\Users\me> ollama pull gpt-oss:latest
pulling manifest
Error: pull model manifest: 412:

The model you are attempting to pull requires a newer version of Ollama.

Please download the latest version at:

        https://ollama.com/download


PS C:\Users\me> ollama -v
ollama version is 0.4.6
Warning: client version is 0.13.0
PS C:\Users\me>

Server Console output:
PS C:\Users\me> ollama serve
time=2025-11-28T15:29:47.669+01:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\__AI\\.models\\ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-28T15:29:47.731+01:00 level=INFO source=images.go:522 msg="total blobs: 0"
time=2025-11-28T15:29:47.732+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-28T15:29:47.741+01:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)"
time=2025-11-28T15:29:47.744+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-28T15:29:47.749+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65118"
time=2025-11-28T15:29:50.233+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65125"
time=2025-11-28T15:29:50.717+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65130"
time=2025-11-28T15:29:50.955+01:00 level=INFO source=runner.go:102 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2025-11-28T15:29:50.956+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-e810ccfa-f88b-89f1-2abe-5839b1df2a1d filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA RTX A6000" libdirs=ollama,cuda_v12 driver=12.4 pci_id=0000:01:00.0 type=discrete total="48.0 GiB" available="46.8 GiB"
[GIN] 2025/11/28 - 15:30:04 | 200 |      1.0838ms |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/28 - 15:30:21 | 200 |            0s |       127.0.0.1 | HEAD     "/"
time=2025-11-28T15:30:22.259+01:00 level=INFO source=download.go:177 msg="downloading e7b273f96360 in 16 862 MB part(s)"
PS C:\Users\me>

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.13.0

Originally created by @AMueckl on GitHub (Nov 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13266 ### What is the issue? After having uninstalled Ollama, wiped-off all residual windows registry entries, rebooted Windows, re-installed Ollama using OllamaSetup.exe, downloaded from github Release 0.13.0, I tried to pull gpt-oss:latest. The output below is the console output after the installation was completed. It can be seen that: - ollama -v shows version 0.13.0 - ollama pull gpt-oss:latest stops after approx. 140MB - a retry of ollama pull gpt-oss:latest yielded: "Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama." - ollama -v then shows a different version 0.4.6, while the client version still is at 0.13.0 Note: The steps observed happend within 1-2 minutes, there had not been any other interactions with the computer. ### Relevant log output ```shell Working Console output: PS C:\Users\me> ollama -v ollama version is 0.13.0 PS C:\Users\me> ollama pull gpt-oss:latest pulling manifest pulling e7b273f96360: 1% ▕ ▏ 140 MB/ 13 GB 6.3 MB/s 36m21s PS C:\Users\me> ollama pull gpt-oss:latest pulling manifest Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama. Please download the latest version at: https://ollama.com/download PS C:\Users\me> ollama -v ollama version is 0.4.6 Warning: client version is 0.13.0 PS C:\Users\me> Server Console output: PS C:\Users\me> ollama serve time=2025-11-28T15:29:47.669+01:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\__AI\\.models\\ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]" time=2025-11-28T15:29:47.731+01:00 level=INFO source=images.go:522 msg="total blobs: 0" time=2025-11-28T15:29:47.732+01:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-28T15:29:47.741+01:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)" time=2025-11-28T15:29:47.744+01:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-28T15:29:47.749+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65118" time=2025-11-28T15:29:50.233+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65125" time=2025-11-28T15:29:50.717+01:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\ProgramData\\Ollama\\ollama.exe runner --ollama-engine --port 65130" time=2025-11-28T15:29:50.955+01:00 level=INFO source=runner.go:102 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2025-11-28T15:29:50.956+01:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-e810ccfa-f88b-89f1-2abe-5839b1df2a1d filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA RTX A6000" libdirs=ollama,cuda_v12 driver=12.4 pci_id=0000:01:00.0 type=discrete total="48.0 GiB" available="46.8 GiB" [GIN] 2025/11/28 - 15:30:04 | 200 | 1.0838ms | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/28 - 15:30:21 | 200 | 0s | 127.0.0.1 | HEAD "/" time=2025-11-28T15:30:22.259+01:00 level=INFO source=download.go:177 msg="downloading e7b273f96360 in 16 862 MB part(s)" PS C:\Users\me> ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.13.0
GiteaMirror added the bug label 2026-04-22 18:10:52 -05:00
GiteaMirror commented 2026-04-22 18:10:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 28, 2025):

There is an old server running. Did you previously install ollama in WSL?

<!-- gh-comment-id:3589831503 --> @rick-github commented on GitHub (Nov 28, 2025): There is an old server running. Did you previously install ollama in WSL?
GiteaMirror commented 2026-04-22 18:10:55 -05:00
Author
Owner
Copy Link

@AMueckl commented on GitHub (Nov 29, 2025):

First of all thank you very much for your prompt reaction, it triggered me looking into other causes, and I have found it:

The issue stems from Docker Desktop (I currently got the update to version 4.53.0 installed).

When Docker Desktop is not running, ollama -v shows version 0.13.0 as sole version information.

Once I start Docker Desktop, ollama -v shows both:

ollama version is 0.4.6
Warning: client version is 0.13.0

At that time no docker container is running, having Docker Desktop started is sufficient to interfere with ollama.

Closing Docker Desktop and waiting for several seconds, ollama -v shows version 0.13.0 again (sometimes I needed to run a model like ollama run gpt-oss:latest in order to trigger the version information to update).

So I am sorry for bothering you!

But maybe this information is helpful for others running into a similar strange problem.

Thank you very much! Thank you for Ollama - it is a great tool!

<!-- gh-comment-id:3591583700 --> @AMueckl commented on GitHub (Nov 29, 2025): First of all thank you very much for your prompt reaction, it triggered me looking into other causes, and I have found it: The issue stems from Docker Desktop (I currently got the update to version 4.53.0 installed). When Docker Desktop is not running, `ollama -v` shows version 0.13.0 as sole version information. Once I start Docker Desktop, `ollama -v` shows both: ```text ollama version is 0.4.6 Warning: client version is 0.13.0 ``` At that time no docker container is running, having Docker Desktop started is sufficient to interfere with ollama. Closing Docker Desktop and waiting for several seconds, `ollama -v` shows version 0.13.0 again (sometimes I needed to run a model like `ollama run gpt-oss:latest` in order to trigger the version information to update). So I am sorry for bothering you! But maybe this information is helpful for others running into a similar strange problem. Thank you very much! Thank you for Ollama - it is a great tool!
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#34528
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?