github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9752] Is this normal? Gemma3：27b used 38GB of memory on its first run #6371

New Issue
Open
opened 2026-04-12 17:52:58 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 17:52:58 -05:00
Owner
Copy Link

Originally created by @yangtianzhen233 on GitHub (Mar 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9752

What is the issue?

Is this normal? Gemma3 used 38GB of memory on its first run, and then decreased to 23GB after running for a while.

Image Image

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

No response

Originally created by @yangtianzhen233 on GitHub (Mar 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9752 ### What is the issue? Is this normal? Gemma3 used 38GB of memory on its first run, and then decreased to 23GB after running for a while. <img width="623" alt="Image" src="https://github.com/user-attachments/assets/013885e8-bc7c-4ae2-8e87-87515a514cc9" /> <img width="626" alt="Image" src="https://github.com/user-attachments/assets/f655966b-cd79-41c9-9c2c-6f934221dfd1" /> ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 17:52:58 -05:00
GiteaMirror commented 2026-04-12 17:52:59 -05:00
Author
Owner
Copy Link

@tclm commented on GitHub (Mar 14, 2025):

I have the same problem, even more exaggerated, Gemma3:27B model takes up much more memory than qwq:32B.
I use AMD 8845HS CPU / 780M GPU

<!-- gh-comment-id:2723645500 --> @tclm commented on GitHub (Mar 14, 2025): I have the same problem, even more exaggerated, Gemma3:27B model takes up much more memory than qwq:32B. I use AMD 8845HS CPU / 780M GPU
GiteaMirror commented 2026-04-12 17:52:59 -05:00
Author
Owner
Copy Link

@yangtianzhen233 commented on GitHub (Mar 14, 2025):

I have the same problem, even more exaggerated, Gemma3:27B model takes up much more memory than qwq:32B. I use AMD 8845HS CPU / 780M GPU

yep,much much more than gemma2:27b, deepseek r1:32b

<!-- gh-comment-id:2723767072 --> @yangtianzhen233 commented on GitHub (Mar 14, 2025): > I have the same problem, even more exaggerated, Gemma3:27B model takes up much more memory than qwq:32B. I use AMD 8845HS CPU / 780M GPU yep,much much more than gemma2:27b, deepseek r1:32b
GiteaMirror commented 2026-04-12 17:52:59 -05:00
Author
Owner
Copy Link

@wisepmlin commented on GitHub (Mar 14, 2025):

Error: llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade

<!-- gh-comment-id:2724906159 --> @wisepmlin commented on GitHub (Mar 14, 2025): Error: llama runner process has terminated: this model is not supported by your version of Ollama. You may need to upgrade
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#6371
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?