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 #9778] gemma crash #32152

New Issue
Closed
opened 2026-04-22 13:07:27 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 13:07:27 -05:00
Owner
Copy Link

Originally created by @schwaa on GitHub (Mar 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9778

What is the issue?

When using gemma3:27b, it randomly crashes. I can run qwen2.5 32b and deepseek-r1:32b with no issues. I have a laptop 4090. qwen2.5 coder 32b runs pretty fast and no crashes. Not sure what is different about gemma3. I've tried the smaller verisons (12b) and the same problem. I'm running on ubuntu.

Relevant log output

Error: POST predict: Post "http://127.0.0.1:36549/completion": EOF

OS

Ubuntu 22.04.5 LTS

GPU

GeForce RTX 4090

CPU

Intel(R) Core(TM) i9-14900HX

Ollama version

ollama version is 0.6.0

Originally created by @schwaa on GitHub (Mar 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9778 ### What is the issue? When using gemma3:27b, it randomly crashes. I can run qwen2.5 32b and deepseek-r1:32b with no issues. I have a laptop 4090. qwen2.5 coder 32b runs pretty fast and no crashes. Not sure what is different about gemma3. I've tried the smaller verisons (12b) and the same problem. I'm running on ubuntu. ### Relevant log output ```shell Error: POST predict: Post "http://127.0.0.1:36549/completion": EOF ``` ### OS Ubuntu 22.04.5 LTS ### GPU GeForce RTX 4090 ### CPU Intel(R) Core(TM) i9-14900HX ### Ollama version ollama version is 0.6.0
GiteaMirror added the bug label 2026-04-22 13:07:27 -05:00
GiteaMirror commented 2026-04-22 13:07:29 -05:00
Author
Owner
Copy Link

@Revnoplex commented on GitHub (Mar 15, 2025):

I've experience the same random error too when using the API

<!-- gh-comment-id:2726196972 --> @Revnoplex commented on GitHub (Mar 15, 2025): I've experience the same random error too when using the API
GiteaMirror commented 2026-04-22 13:07:30 -05:00
Author
Owner
Copy Link

@mehditahmasebi commented on GitHub (Mar 15, 2025):

Not fixed yet
in ollama version 0.6.1
ollama run gemma3:27b-it-q8_0
Error: Post "http://127.0.0.1:11434/api/generate": EOF

I have overall 64gb RTX vram

<!-- gh-comment-id:2726421303 --> @mehditahmasebi commented on GitHub (Mar 15, 2025): Not fixed yet in ollama version 0.6.1 ollama run gemma3:27b-it-q8_0 Error: Post "http://127.0.0.1:11434/api/generate": EOF I have overall 64gb RTX vram
GiteaMirror commented 2026-04-22 13:07:31 -05:00
Author
Owner
Copy Link

@windisch-paul commented on GitHub (Mar 15, 2025):

Same issue for me for all gemma3 models I've tried. Other models, also larger ones, work fine.

<!-- gh-comment-id:2726496906 --> @windisch-paul commented on GitHub (Mar 15, 2025): Same issue for me for all gemma3 models I've tried. Other models, also larger ones, work fine.
GiteaMirror commented 2026-04-22 13:07:32 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Mar 16, 2025):

Hey folks would it be possible to try 0.6.1 released today? https://github.com/ollama/ollama/releases/tag/v0.6.1 This made some improvements with memory estimation

Going to merge this with https://github.com/ollama/ollama/issues/9791

<!-- gh-comment-id:2727098081 --> @jmorganca commented on GitHub (Mar 16, 2025): Hey folks would it be possible to try 0.6.1 released today? https://github.com/ollama/ollama/releases/tag/v0.6.1 This made some improvements with memory estimation Going to merge this with https://github.com/ollama/ollama/issues/9791
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#32152
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?