github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2968] How to specify which GPU to use when starting Ollama #27583

New Issue
Closed
opened 2026-04-22 05:02:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 05:02:49 -05:00
Owner
Copy Link

Originally created by @lyj555 on GitHub (Mar 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2968

Currently, on Linux, there are two GPUs, and it seems that Ollama is occupying a part of both.
企业微信20240307-101729@2x

Originally created by @lyj555 on GitHub (Mar 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2968 Currently, on Linux, there are two GPUs, and it seems that Ollama is occupying a part of both. <img width="796" alt="企业微信20240307-101729@2x" src="https://github.com/ollama/ollama/assets/20056271/66ececfe-5a0f-471a-a41c-f9373c8510e7">
GiteaMirror commented 2026-04-22 05:02:51 -05:00
Author
Owner
Copy Link

@samavedulark commented on GitHub (Mar 8, 2024):

if you are using docker, which is a better choice, run the below command.
Select an un-occupied GPU just to be clear.
docker run -d --gpus 'device=1' -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

<!-- gh-comment-id:1985052208 --> @samavedulark commented on GitHub (Mar 8, 2024): if you are using docker, which is a better choice, run the below command. Select an un-occupied GPU just to be clear. docker run -d --gpus 'device=1' -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
GiteaMirror commented 2026-04-22 05:02:54 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Mar 12, 2024):

Hi there, there isn't a direct way to decide which GPU to use for Ollama yet. This is something I hope will becoming soon! In the meantime there are some workarounds like CUDA_VISIBLE_DEVICES (https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/) or the Docker workaround @samavedulark mentioned. Stay tuned for more!

<!-- gh-comment-id:1989670207 --> @jmorganca commented on GitHub (Mar 12, 2024): Hi there, there isn't a direct way to decide which GPU to use for Ollama yet. This is something I hope will becoming soon! In the meantime there are some workarounds like `CUDA_VISIBLE_DEVICES` (https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/) or the Docker workaround @samavedulark mentioned. Stay tuned for more!
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#27583
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?