github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11493] Add possibility to setup GPU priority. #85277

New Issue
Closed
opened 2026-05-09 22:57:16 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-09 22:57:16 -05:00
Owner
Copy Link

Originally created by @Crandel on GitHub (Jul 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11493

I have 2 GPU setup, one GPU is NVIDIA with 6 Gb RAM, and another one is AMD with 24 Gb RAM. Ollama always choose AMD GPU even if model(Gemma 3) fits to NVIDIA GPU, which is way faster than AMD GPU. Is there any way to prioritize NVIDIA GPU over AMD?

Originally created by @Crandel on GitHub (Jul 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11493 I have 2 GPU setup, one GPU is NVIDIA with 6 Gb RAM, and another one is AMD with 24 Gb RAM. Ollama always choose AMD GPU even if model(Gemma 3) fits to NVIDIA GPU, which is way faster than AMD GPU. Is there any way to prioritize NVIDIA GPU over AMD?
GiteaMirror added the feature request label 2026-05-09 22:57:16 -05:00
GiteaMirror commented 2026-05-09 22:57:18 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 22, 2025):

Try setting main_gpu.

<!-- gh-comment-id:3102391249 --> @rick-github commented on GitHub (Jul 22, 2025): Try setting [`main_gpu`](https://github.com/ollama/ollama/blob/82da19c634b6cb2e72d6d648b278f1a1bfcc1e0c/docs/api.md?plain=1#L404).
GiteaMirror commented 2026-05-09 22:57:18 -05:00
Author
Owner
Copy Link

@Crandel commented on GitHub (Jul 22, 2025):

Is it possible to do via env variables? I'm not controlling ollama clients which should use ollama

<!-- gh-comment-id:3102419170 --> @Crandel commented on GitHub (Jul 22, 2025): Is it possible to do via env variables? I'm not controlling ollama clients which should use ollama
GiteaMirror commented 2026-05-09 22:57:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 11, 2025):

There isn't an environment variable for controlling main_gpu, but you should be able to set it as a parameter in the Modelfile:

echo FROM gemma3 > Modelfile
echo PARAMETER main_gpu 1 >> Modelfile
ollama create gemma3:gpu1
<!-- gh-comment-id:3177051962 --> @rick-github commented on GitHub (Aug 11, 2025): There isn't an environment variable for controlling `main_gpu`, but you should be able to set it as a parameter in the Modelfile: ```console echo FROM gemma3 > Modelfile echo PARAMETER main_gpu 1 >> Modelfile ollama create gemma3:gpu1 ```
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 feature request
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#85277
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?