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 #9695] Gemma3 27B uses 2.5x VRAM of Gemma2 27B #52841

New Issue
Closed
opened 2026-04-29 01:07:39 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 01:07:39 -05:00
Owner
Copy Link

Originally created by @hg0428 on GitHub (Mar 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9695

What is the issue?

https://discord.com/channels/1128867683291627614/1349413021805580461/1349413021805580461

Gemma3 27B Q4_K_M is using 40GB of memory, while I only have 36GB. Gemma2 27B did not do this and used far less.

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.6.0

Originally created by @hg0428 on GitHub (Mar 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9695 ### What is the issue? https://discord.com/channels/1128867683291627614/1349413021805580461/1349413021805580461 Gemma3 27B Q4_K_M is using 40GB of memory, while I only have 36GB. Gemma2 27B did not do this and used far less. ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-29 01:07:39 -05:00
GiteaMirror commented 2026-04-29 01:07:46 -05:00
Author
Owner
Copy Link

@EldanRing commented on GitHub (Mar 12, 2025):

I'm having the same issue, all of Gemma 3 models are using an absurd amount of memory. Also testing in macOS with an M4 pro.

<!-- gh-comment-id:2718572962 --> @EldanRing commented on GitHub (Mar 12, 2025): I'm having the same issue, all of Gemma 3 models are using an absurd amount of memory. Also testing in macOS with an M4 pro.
GiteaMirror commented 2026-04-29 01:07:49 -05:00
Author
Owner
Copy Link

@sirajperson commented on GitHub (Mar 12, 2025):

I'm having the same issue on Ubuntu 24.04. The model seems to have loaded to the GPU, but there are like 47 processes associated wit attempting to run it. Ollama eventually times out:

ollama run gemma3:27b-it-fp16
Error: timed out waiting for llama runner to start - progress 0.00 -

After exiting ollama, Gemma stays in the GPUs and the process that were trying to continue to run on.

<!-- gh-comment-id:2718692785 --> @sirajperson commented on GitHub (Mar 12, 2025): I'm having the same issue on Ubuntu 24.04. The model seems to have loaded to the GPU, but there are like 47 processes associated wit attempting to run it. Ollama eventually times out: ollama run gemma3:27b-it-fp16 Error: timed out waiting for llama runner to start - progress 0.00 - After exiting ollama, Gemma stays in the GPUs and the process that were trying to continue to run on.
GiteaMirror commented 2026-04-29 01:07:49 -05:00
Author
Owner
Copy Link

@Igorgro commented on GitHub (Mar 12, 2025):

Having the same issue. I have no problem running qwen2.5:32b which exactly fits into my 24Gb of VRAM, but Gemma3 eats the whole VRAM and then starts to offloading to RAM. It eats whole 24Gb of RAM and get killed by OOM.

<!-- gh-comment-id:2718748190 --> @Igorgro commented on GitHub (Mar 12, 2025): Having the same issue. I have no problem running qwen2.5:32b which exactly fits into my 24Gb of VRAM, but Gemma3 eats the whole VRAM and then starts to offloading to RAM. It eats whole 24Gb of RAM and get killed by OOM.
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#52841
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?