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 #2227] model not loading in GPU #27036

New Issue
Closed
opened 2026-04-22 03:56:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 03:56:33 -05:00
Owner
Copy Link

Originally created by @muka on GitHub (Jan 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2227

Hi, great project congrats!

I noticed that event if ollama (in docker) logs say it offloaded layers to GPU

image

nvdia-smi report no actual usage

image

Is this an expected beahviour?

A similar setup with localai has similar logs but with better performances, denoting it is actually using the gpu

Originally created by @muka on GitHub (Jan 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2227 Hi, great project congrats! I noticed that event if ollama (in docker) logs say it offloaded layers to GPU ![image](https://github.com/ollama/ollama/assets/1021269/e21f2348-22c9-43ab-84dd-232c9a75a019) nvdia-smi report no actual usage ![image](https://github.com/ollama/ollama/assets/1021269/0cb21d32-e5f9-42de-b56f-eafe045c3bbe) Is this an expected beahviour? A similar setup with [localai](https://github.com/mudler/LocalAI) has similar logs but with better performances, denoting it is actually using the gpu
GiteaMirror commented 2026-04-22 03:56:34 -05:00
Author
Owner
Copy Link

@muka commented on GitHub (Jan 27, 2024):

Dumb me, actually ollama was logging it could not load the model in GPU.

This already happened to me when linux comes back from hibernation.

This may help or a full reboot as last resort

sudo rmmod nvidia_uvm || true
sudo modprobe nvidia_uvm  || true

ollama is running at full speed now, great!

Self closing 🥇

<!-- gh-comment-id:1913091607 --> @muka commented on GitHub (Jan 27, 2024): Dumb me, actually ollama was logging it could not load the model in GPU. This already happened to me when linux comes back from hibernation. This may help or a full reboot as last resort ```sh sudo rmmod nvidia_uvm || true sudo modprobe nvidia_uvm || true ``` ollama is running at full speed now, great! Self closing :1st_place_medal:
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#27036
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?