github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7672] Moondream v2 (CPU) crashes with images (post predict EOF error) on 0.4.1 #51407

New Issue
Closed
opened 2026-04-28 19:53:22 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 19:53:22 -05:00
Owner
Copy Link

Originally created by @rvkwi on GitHub (Nov 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7672

What is the issue?

Moondream v2 seems to run into an issue with images on CPU with 0.4.1,
resulting in Error: POST predict: Post "http://127.0.0.1:33685/completion": EOF.
Does not seem to affect GPU.

~ $ ollama run moondream:v2 "please describe this image /home/kwi/demo-2.png" --verbose
Added image '/home/kwi/demo-2.png'
Error: POST predict: Post "http://127.0.0.1:34833/completion": EOF
~ $ ollama run moondream:v2 hi

 Hi

$ ollama --version
ollama version is 0.4.1

Only seems to happen with images, not text. The model loads and runs fine for text chat, but consistently crashes with EOF when attempting to process any image.

journalctl:
level=DEBUG source=server.go:423 msg="llama runner terminated" error="signal: aborted"

What i tried so far.

  • Differen images
  • Different CPUS (Ryzen 5 6600H, Ryzen 7 5700X, i5-3320M)
  • Other vision models (minicpm-v and llama seem to work fine)
  • Different quants
  • CLI and through API

I had an older laptop around with an outdated ollama 0.3.1 on it, that still worked fine. Upgrading to 0.4.1 caused the exact same error to appear as well.

OS

Linux

GPU

No response

CPU

Intel, AMD

Ollama version

0.4.1

Originally created by @rvkwi on GitHub (Nov 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7672 ### What is the issue? Moondream v2 seems to run into an issue with images on CPU with 0.4.1, resulting in `Error: POST predict: Post "http://127.0.0.1:33685/completion": EOF`. Does not seem to affect GPU. ``` ~ $ ollama run moondream:v2 "please describe this image /home/kwi/demo-2.png" --verbose Added image '/home/kwi/demo-2.png' Error: POST predict: Post "http://127.0.0.1:34833/completion": EOF ~ $ ollama run moondream:v2 hi Hi $ ollama --version ollama version is 0.4.1 ``` Only seems to happen with images, not text. The model loads and runs fine for text chat, but consistently crashes with EOF when attempting to process any image. journalctl: `level=DEBUG source=server.go:423 msg="llama runner terminated" error="signal: aborted"` What i tried so far. - Differen images - Different CPUS (Ryzen 5 6600H, Ryzen 7 5700X, i5-3320M) - Other vision models (minicpm-v and llama seem to work fine) - Different quants - CLI and through API I had an older laptop around with an outdated ollama 0.3.1 on it, that still worked fine. Upgrading to 0.4.1 caused the exact same error to appear as well. ### OS Linux ### GPU _No response_ ### CPU Intel, AMD ### Ollama version 0.4.1
GiteaMirror added the bug label 2026-04-28 19:53:22 -05:00
GiteaMirror commented 2026-04-28 19:53:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 14, 2024):

probably #7441.

Server logs would clarify.

<!-- gh-comment-id:2477550472 --> @rick-github commented on GitHub (Nov 14, 2024): probably #7441. [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) would clarify.
GiteaMirror commented 2026-04-28 19:53:29 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 14, 2024):

Yes, I think this is #7441 - let's track it there.

<!-- gh-comment-id:2477553467 --> @jessegross commented on GitHub (Nov 14, 2024): Yes, I think this is #7441 - let's track it there.
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#51407
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?