github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8260] For CPU systems, getting files which are being used for GPU #67336

New Issue
Closed
opened 2026-05-04 09:57:28 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 09:57:28 -05:00
Owner
Copy Link

Originally created by @Abubakkar13 on GitHub (Dec 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8260

What is the issue?

Hey,

Happy holidays 😍!!!

I just came across with Ollama version update, then saw some files are being downloaded, I noticed that few dll libraries are being download, So i just cross checked the folder there are 7 files(Specifically starting with cuda* or cublas* ) and in runners folder as well, have downloaded. But these are for GPU acceleration, since i am with CPU only, is their a way to ignore these files or is their a way to do a system check just before installing the Ollama so can ignore while installing itself, so it can reduce 2.8GB of space for CPU users?

Folder is:

  1. Taking around 880M: C:\Users[USER}\AppData\Local\Programs\Ollama\lib\ollama

image

  1. Taking around 2GB: C:\Users[USER]\AppData\Local\Programs\Ollama\lib\ollama\runners

image

Thank you
From GPU Poor 😅

OS

Windows

GPU

No response

CPU

Intel

Ollama version

0.5.4

Originally created by @Abubakkar13 on GitHub (Dec 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8260 ### What is the issue? Hey, Happy holidays 😍!!! I just came across with Ollama version update, then saw some files are being downloaded, I noticed that few dll libraries are being download, So i just cross checked the folder there are 7 files(Specifically starting with **cuda*** or **cublas*** ) and in runners folder as well, have downloaded. But these are for GPU acceleration, since i am with CPU only, is their a way to ignore these files or is their a way to do a system check just before installing the Ollama so can ignore while installing itself, so it can reduce 2.8GB of space for CPU users? Folder is: 1. Taking around 880M: C:\Users\[USER}\AppData\Local\Programs\Ollama\lib\ollama ![image](https://github.com/user-attachments/assets/3982eb88-d4c9-4283-ab76-099c7873cb94) 2. Taking around 2GB: C:\Users\[USER]\AppData\Local\Programs\Ollama\lib\ollama\runners ![image](https://github.com/user-attachments/assets/37f259f6-4c6f-4d25-b245-a815eba34ace) Thank you From GPU Poor 😅 ### OS Windows ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-05-04 09:57:28 -05:00
GiteaMirror commented 2026-05-04 09:57:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 28, 2024):

https://github.com/ollama/ollama/issues/8234

<!-- gh-comment-id:2564184220 --> @rick-github commented on GitHub (Dec 28, 2024): https://github.com/ollama/ollama/issues/8234
GiteaMirror commented 2026-05-04 09:57:31 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 29, 2024):

Closing this as a dupe.

<!-- gh-comment-id:2564597542 --> @pdevine commented on GitHub (Dec 29, 2024): Closing this as a dupe.
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#67336
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?