github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13986] docs: Restore num_gpu as a valid Modelfile parameter #71206

New Issue
Open
opened 2026-05-05 00:40:43 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-05 00:40:43 -05:00
Owner
Copy Link

Originally created by @oyale on GitHub (Jan 30, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13986

Hi!

I noticed num_gpu was removed from the Modelfile parameter's documentation in e54a3c7, despite still being functional (at least to force CPU execution).

Adding this parameter to the Modelfile is currently the only way I've found to ensure a specific model doesn't load on the GPU without modifying the API request. I spent quite a while searching for a solution elsewhere since it was missing from the official docs (fortunately, there are a lot of answers to issues that mention it).

Would you consider restoring it to the documentation?

Originally created by @oyale on GitHub (Jan 30, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13986 Hi! I noticed `num_gpu` was removed from the Modelfile parameter's documentation in e54a3c7, despite still being functional (at least to force CPU execution). Adding this parameter to the Modelfile is currently the only way I've found to ensure a specific model doesn't load on the GPU without modifying the API request. I spent quite a while searching for a solution elsewhere since it was missing from the official docs (fortunately, there are a lot of answers to issues that mention it). Would you consider restoring it to the documentation?
GiteaMirror added the documentation label 2026-05-05 00:40:43 -05:00
GiteaMirror commented 2026-05-05 00:40:45 -05:00
Author
Owner
Copy Link

@mvanhorn commented on GitHub (Mar 9, 2026):

I've submitted a fix in the PR above. Restored the num_gpu parameter entry that was accidentally dropped from the Modelfile documentation.

<!-- gh-comment-id:4024409084 --> @mvanhorn commented on GitHub (Mar 9, 2026): I've submitted a fix in the PR above. Restored the num_gpu parameter entry that was accidentally dropped from the Modelfile documentation.
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 documentation
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#71206
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?