github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9821] Models have different weights in process status #32190

New Issue
Closed
opened 2026-04-22 13:13:55 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 13:13:55 -05:00
Owner
Copy Link

Originally created by @DavidePrati99 on GitHub (Mar 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9821

What is the issue?

why phi4 14b (that weights 9.1gb) in ps has a weight of 13 gb while gemma3:12b, that weights less (8.1gb) weights more in ps (16 gb)?

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @DavidePrati99 on GitHub (Mar 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9821 ### What is the issue? why phi4 14b (that weights 9.1gb) in ps has a weight of 13 gb while gemma3:12b, that weights less (8.1gb) weights more in ps (16 gb)? ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the question label 2026-04-22 13:13:55 -05:00
GiteaMirror commented 2026-04-22 13:14:02 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 17, 2025):

#9791

<!-- gh-comment-id:2729731317 --> @rick-github commented on GitHub (Mar 17, 2025): #9791
GiteaMirror commented 2026-04-22 13:14:02 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 17, 2025):

While most of gemma3 is quantized there is also a non-quantized vision component which is what causes the consumed memory to be larger.

There is also a memory leak w/ gemma3 which will be patched later today and released w/ 0.6.2 which @rick-github was alluding to.

I'll go ahead and close the issue as answered.

<!-- gh-comment-id:2730376613 --> @pdevine commented on GitHub (Mar 17, 2025): While most of gemma3 is quantized there is also a non-quantized vision component which is what causes the consumed memory to be larger. There is also a memory leak w/ gemma3 which will be patched later today and released w/ `0.6.2` which @rick-github was alluding to. I'll go ahead and close the issue as answered.
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 question
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#32190
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?