github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9908] gemma3:27b not working #53000

New Issue
Closed
opened 2026-04-29 01:37:32 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 01:37:32 -05:00
Owner
Copy Link

Originally created by @jankogasic on GitHub (Mar 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9908

What is the issue?

I am unable to make gemma3:27b work.

Image

Llama3.3:70B and gemma3:4b are working.

from nvidia-smi output it seems that entire 17GB of model are loaded onto GPU.

docker-compose.yaml:

Image

Relevant log output

OS

Docker

GPU

Nvidia

CPU

AMD

Ollama version

Tried both 0.6.1 and 0.6.2

Originally created by @jankogasic on GitHub (Mar 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9908 ### What is the issue? I am unable to make `gemma3:27b` work. <img width="1320" alt="Image" src="https://github.com/user-attachments/assets/ebc56b4b-8753-4664-8cd4-775bd78383e0" /> `Llama3.3:70B` and `gemma3:4b` are working. from `nvidia-smi` output it seems that entire 17GB of model are loaded onto GPU. docker-compose.yaml: <img width="516" alt="Image" src="https://github.com/user-attachments/assets/6a34a6c5-83e1-470c-9295-305d20fb0b58" /> ### Relevant log output ```shell ``` ### OS Docker ### GPU Nvidia ### CPU AMD ### Ollama version Tried both 0.6.1 and 0.6.2
GiteaMirror added the bug label 2026-04-29 01:37:32 -05:00
GiteaMirror commented 2026-04-29 01:37:38 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 20, 2025):

Server logs may aid in debugging. But be aware that gemma3 has a substantial system RAM footprint at the moment - :27b wants about 13G, so I suspect that the memory: 8g line in your docker config, combined with llama runner process has terminated: signal: killed, means that your kernel killed the runner due to OOM.

<!-- gh-comment-id:2740741698 --> @rick-github commented on GitHub (Mar 20, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) may aid in debugging. But be aware that gemma3 has a substantial system RAM footprint at the moment - :27b wants about 13G, so I suspect that the `memory: 8g` line in your docker config, combined with `llama runner process has terminated: signal: killed`, means that your kernel killed the runner due to OOM.
GiteaMirror commented 2026-04-29 01:37:39 -05:00
Author
Owner
Copy Link

@jankogasic commented on GitHub (Mar 20, 2025):

That's it. It's working now. Too bad docker logs are not more precise in this case.

Thanks!

<!-- gh-comment-id:2740974739 --> @jankogasic commented on GitHub (Mar 20, 2025): That's it. It's working now. Too bad docker logs are not more precise in this case. Thanks!
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#53000
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?