github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12608] Error occurred when starting the model #8369

New Issue
Closed
opened 2026-04-12 20:59:20 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 20:59:20 -05:00
Owner
Copy Link

Originally created by @ZhongxuTang on GitHub (Oct 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12608

What is the issue?

When I started the model, an error occurred，and log file has no output
Error: 500 Internal Server Error: load unmarshal encode response: json: cannot unmarshal number into Go struct field BackendMemory.Memory.InputWeights of type ml.Memory

Image

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.12.3

Originally created by @ZhongxuTang on GitHub (Oct 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12608 ### What is the issue? When I started the model, an error occurred，and log file has no output Error: 500 Internal Server Error: load unmarshal encode response: json: cannot unmarshal number into Go struct field BackendMemory.Memory.InputWeights of type ml.Memory <img width="1413" height="318" alt="Image" src="https://github.com/user-attachments/assets/81149d66-d63d-46ee-9b11-ffb7fd4b2fa3" /> ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.12.3
GiteaMirror added the bugmacos labels 2026-04-12 20:59:20 -05:00
GiteaMirror commented 2026-04-12 20:59:23 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 14, 2025):

@ZhongxuTang did you install the client separately from the server? I'm confused why the client is a newer version.

<!-- gh-comment-id:3403503710 --> @pdevine commented on GitHub (Oct 14, 2025): @ZhongxuTang did you install the client separately from the server? I'm confused why the client is a newer version.
GiteaMirror commented 2026-04-12 20:59:23 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Oct 14, 2025):

This is probably caused by the ollama server binary in memory being older than the one on disk, which is used to launch the runner. This likely happened after upgrade and should be fixed by restarting the server. This should also fix the client/server version mismatch.

<!-- gh-comment-id:3403616927 --> @jessegross commented on GitHub (Oct 14, 2025): This is probably caused by the ollama server binary in memory being older than the one on disk, which is used to launch the runner. This likely happened after upgrade and should be fixed by restarting the server. This should also fix the client/server version mismatch.
GiteaMirror commented 2026-04-12 20:59:24 -05:00
Author
Owner
Copy Link

@johnnynunez commented on GitHub (Oct 14, 2025):

sudo systemctl daemon-reload
sudo systemctl restart ollama
<!-- gh-comment-id:3403817053 --> @johnnynunez commented on GitHub (Oct 14, 2025): ``` sudo systemctl daemon-reload sudo systemctl restart ollama ```
GiteaMirror commented 2026-04-12 20:59:25 -05:00
Author
Owner
Copy Link

@ZhongxuTang commented on GitHub (Oct 15, 2025):

I solved this problem by upgrading the client, but I still don't understand why a lagging client version can affect the use of the server.

<!-- gh-comment-id:3404217347 --> @ZhongxuTang commented on GitHub (Oct 15, 2025): I solved this problem by upgrading the client, but I still don't understand why a lagging client version can affect the use of the server.
GiteaMirror commented 2026-04-12 20:59:26 -05:00
Author
Owner
Copy Link

@ZhongxuTang commented on GitHub (Oct 15, 2025):

@ZhongxuTang did you install the client separately from the server? I'm confused why the client is a newer version.

Yes, that is the reason for it.

<!-- gh-comment-id:3404220392 --> @ZhongxuTang commented on GitHub (Oct 15, 2025): > [@ZhongxuTang](https://github.com/ZhongxuTang) did you install the client separately from the server? I'm confused why the client is a newer version. Yes, that is the reason for it.
GiteaMirror commented 2026-04-12 20:59:27 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 15, 2025):

@ZhongxuTang I believe @jessegross 's answer is correct. Just running an old binary for the server without restarting. The client gets restarted every time you type a command.

<!-- gh-comment-id:3404404855 --> @pdevine commented on GitHub (Oct 15, 2025): @ZhongxuTang I believe @jessegross 's answer is correct. Just running an old binary for the server without restarting. The client gets restarted every time you type a command.
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 macos
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#8369
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?