github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13657] Homebrew install on Linux does not support NVIDIA GPU inference (CUDA) — please document in README #55489

New Issue
Open
opened 2026-04-29 09:17:33 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 09:17:33 -05:00
Owner
Copy Link

Originally created by @nc1m on GitHub (Jan 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13657

Hello,

When installing ollama via Homebrew, NVIDIA GPU inference (CUDA) is not supported. This isn’t obvious from the current installation instructions, and I spent ~1 hour troubleshooting before finding the cause.

There’s an existing Homebrew-core discussion indicating this limitation:

Request
Could you please add a short note to the README "Package managers" section clarifying that the Homebrew formula does not support NVIDIA GPU inference (CUDA), and that users who need CUDA should use an alternative installation method (e.g., the official installer/package or build-from-source instructions)?

Why this matters
Without a note, users with NVIDIA GPUs may assume GPU acceleration should work out of the box after brew install ollama, and end up debugging drivers/CUDA/tooling unnecessarily.

Thanks for considering!

Originally created by @nc1m on GitHub (Jan 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13657 Hello, When installing `ollama` via Homebrew, NVIDIA GPU inference (CUDA) is not supported. This isn’t obvious from the current installation instructions, and I spent ~1 hour troubleshooting before finding the cause. There’s an existing Homebrew-core discussion indicating this limitation: - https://github.com/Homebrew/homebrew-core/issues/260946 **Request** Could you please add a short note to the README "Package managers" section clarifying that the Homebrew formula does not support NVIDIA GPU inference (CUDA), and that users who need CUDA should use an alternative installation method (e.g., the official installer/package or build-from-source instructions)? **Why this matters** Without a note, users with NVIDIA GPUs may assume GPU acceleration should work out of the box after `brew install ollama`, and end up debugging drivers/CUDA/tooling unnecessarily. Thanks for considering!
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#55489
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?