github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15459] macOS Apple Silicon: x/z-image-turbo fails because libmlxc.dylib in Ollama.app is x86_64 #9882

New Issue
Closed
opened 2026-04-12 22:44:34 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 22:44:34 -05:00
Owner
Copy Link

Originally created by @cdevroe on GitHub (Apr 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15459

What is the issue?

I’m on an Apple Silicon Mac and ollama run x/z-image-turbo fails immediately.

This worked for me on February 26, 2026. Just in case it would help, I reinstalled Ollama, but the issue is still happening.

What I see:

  • uname -m -> arm64
  • file /Applications/Ollama.app/Contents/Resources/libmlxc.dylib -> Mach-O 64-bit dynamically linked shared library x86_64
  • file /Applications/Ollama.app/Contents/MacOS/Ollama -> universal binary with x86_64 and arm64

Server log shows Ollama starting an MLX image runner for x/z-image-turbo, then failing to initialize MLX because libmlxc.dylib is the wrong architecture.

Please let me know if there are any other details that I can provide that would help isolate the issue.

OS

macOS 26.4

CPU

M4 Pro

Ollama version

0.20.4

Originally created by @cdevroe on GitHub (Apr 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15459 ### What is the issue? I’m on an Apple Silicon Mac and `ollama run x/z-image-turbo` fails immediately. This worked for me on February 26, 2026. Just in case it would help, I reinstalled Ollama, but the issue is still happening. What I see: - `uname -m` -> `arm64` - `file /Applications/Ollama.app/Contents/Resources/libmlxc.dylib` -> `Mach-O 64-bit dynamically linked shared library x86_64` - `file /Applications/Ollama.app/Contents/MacOS/Ollama` -> universal binary with `x86_64` and `arm64` Server log shows Ollama starting an MLX image runner for `x/z-image-turbo`, then failing to initialize MLX because `libmlxc.dylib` is the wrong architecture. Please let me know if there are any other details that I can provide that would help isolate the issue. ### OS macOS 26.4 ### CPU M4 Pro ### Ollama version 0.20.4
GiteaMirror added the bug label 2026-04-12 22:44:34 -05:00
GiteaMirror commented 2026-04-12 22:44:36 -05:00
Author
Owner
Copy Link

@cdevroe commented on GitHub (Apr 9, 2026):

Sorry for the duplicate! I didn't think to search closed issues. Glad it is going to be resolved though! Thank you! 🙏

<!-- gh-comment-id:4216583209 --> @cdevroe commented on GitHub (Apr 9, 2026): Sorry for the duplicate! I didn't think to search closed issues. Glad it is going to be resolved though! Thank you! 🙏
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 bug
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#9882
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?