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 #2064] gpu #26954

New Issue
Closed
opened 2026-04-22 03:45:00 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 03:45:00 -05:00
Owner
Copy Link

Originally created by @iplayfast on GitHub (Jan 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2064

I tried running ollama on a laptop and noticed that it wasn't using gpu. I don't know why as cuda is installed and is the correct version for the video drivers.
I'd like to request an enhancement, of an error message that says something to the effect of gpu noticed but not used because....

I'd also like to be able to see the message when running ollama, something like
/show ollamasystem

Originally created by @iplayfast on GitHub (Jan 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2064 I tried running ollama on a laptop and noticed that it wasn't using gpu. I don't know why as cuda is installed and is the correct version for the video drivers. I'd like to request an enhancement, of an error message that says something to the effect of gpu noticed but not used because.... I'd also like to be able to see the message when running ollama, something like /show ollamasystem
GiteaMirror commented 2026-04-22 03:45:01 -05:00
Author
Owner
Copy Link

@Titaniumtown commented on GitHub (Jan 20, 2024):

Could you provide more information about your computer and what OS you're running and such?

<!-- gh-comment-id:1901628810 --> @Titaniumtown commented on GitHub (Jan 20, 2024): Could you provide more information about your computer and what OS you're running and such?
GiteaMirror commented 2026-04-22 03:45:02 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (Jan 20, 2024):

Same issue here - I'm running Fedora 39 server with GPU drivers installed
Driver Version: 545.29.06 CUDA Version: 12.3
NVIDIA GeForce GTX 950M

Yet when running a model the GPU does nothing

<!-- gh-comment-id:1902170807 --> @DuckyBlender commented on GitHub (Jan 20, 2024): Same issue here - I'm running Fedora 39 server with GPU drivers installed Driver Version: 545.29.06 CUDA Version: 12.3 NVIDIA GeForce GTX 950M Yet when running a model the GPU does nothing
GiteaMirror commented 2026-04-22 03:45:02 -05:00
Author
Owner
Copy Link

@iplayfast commented on GitHub (Jan 22, 2024):

laptop has gtx960m nvidia running linux-mint with cuda 12 installed.

<!-- gh-comment-id:1904634250 --> @iplayfast commented on GitHub (Jan 22, 2024): laptop has gtx960m nvidia running linux-mint with cuda 12 installed.
GiteaMirror commented 2026-04-22 03:45:03 -05:00
Author
Owner
Copy Link

@iplayfast commented on GitHub (Feb 5, 2024):

Latest version fixed this bug

<!-- gh-comment-id:1926337039 --> @iplayfast commented on GitHub (Feb 5, 2024): Latest version fixed this bug
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
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#26954
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?