github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 14:43:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13828] Model x/z-image-pro not working on AMD APU #71115

New Issue
Closed
opened 2026-05-05 00:24:00 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-05 00:24:00 -05:00
Owner
Copy Link

Originally created by @PaulMatthieu on GitHub (Jan 21, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13828

What is the issue?

This model: https://ollama.com/x/z-image-turbo

which ollama recently announced as part of the library, doesn't seem to work on an AMD Ryzen AI MAX+ 395, because it seemingly tries to load a CUDA library

I tried both ollama run x/z-image-turbo:bf16 and ollama run x/z-image-turbo

I fully understand those are experimental so I wasn't expecting everything to be smooth but the limitation should be written in the model's documentation I think?

Relevant log output

Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=INFO source=server.go:149 msg="starting ollama-mlx image runner subprocess" exe=/usr/local/bin/ollama-mlx model=x/z-image-turbo:bf16 port=35259
Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=INFO source=server.go:320 msg="stopping image runner subprocess" pid=46665
Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=WARN source=server.go:141 msg=image-runner msg="/usr/local/bin/ollama-mlx: error while loading shared libraries: libcuda.so.1: cannot open shared object file: No such file or directory"
Jan 21 23:00:46 computer-3 ollama[41718]: [GIN] 2026/01/21 - 23:00:46 | 500 |  5.009672662s |       127.0.0.1 | POST     "/api/generate"

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.14.2

Originally created by @PaulMatthieu on GitHub (Jan 21, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13828 ### What is the issue? This model: https://ollama.com/x/z-image-turbo which ollama recently announced as part of the library, doesn't seem to work on an AMD Ryzen AI MAX+ 395, because it seemingly tries to load a CUDA library I tried both `ollama run x/z-image-turbo:bf16` and `ollama run x/z-image-turbo` I fully understand those are experimental so I wasn't expecting everything to be smooth but the limitation should be written in the model's documentation I think? ### Relevant log output ```shell Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=INFO source=server.go:149 msg="starting ollama-mlx image runner subprocess" exe=/usr/local/bin/ollama-mlx model=x/z-image-turbo:bf16 port=35259 Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=INFO source=server.go:320 msg="stopping image runner subprocess" pid=46665 Jan 21 23:00:41 computer-3 ollama[41718]: time=2026-01-21T23:00:41.054+01:00 level=WARN source=server.go:141 msg=image-runner msg="/usr/local/bin/ollama-mlx: error while loading shared libraries: libcuda.so.1: cannot open shared object file: No such file or directory" Jan 21 23:00:46 computer-3 ollama[41718]: [GIN] 2026/01/21 - 23:00:46 | 500 | 5.009672662s | 127.0.0.1 | POST "/api/generate" ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.14.2
GiteaMirror added the bug label 2026-05-05 00:24:00 -05:00
GiteaMirror commented 2026-05-05 00:24:10 -05:00
Author
Owner
Copy Link

@PaulMatthieu commented on GitHub (Jan 21, 2026):

seems to be the same for x/flux2-klein:9b

<!-- gh-comment-id:3781437878 --> @PaulMatthieu commented on GitHub (Jan 21, 2026): seems to be the same for x/flux2-klein:9b
GiteaMirror commented 2026-05-05 00:24:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 21, 2026):

Linux is not supported yet.

<!-- gh-comment-id:3781583680 --> @rick-github commented on GitHub (Jan 21, 2026): [Linux is not supported yet.](https://github.com/ollama/ollama/releases/tag/v0.14.3)
GiteaMirror commented 2026-05-05 00:24:25 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Jan 22, 2026):

hey @PaulMatthieu - so sorry about this. During the announcement of this, we are doing experimental image generation on macOS only as we build support across Windows and Linux for different hardware.

https://ollama.com/blog/image-generation

<!-- gh-comment-id:3786218588 --> @mchiang0610 commented on GitHub (Jan 22, 2026): hey @PaulMatthieu - so sorry about this. During the announcement of this, we are doing experimental image generation on macOS only as we build support across Windows and Linux for different hardware. https://ollama.com/blog/image-generation
GiteaMirror commented 2026-05-05 00:24:29 -05:00
Author
Owner
Copy Link

@PaulMatthieu commented on GitHub (Jan 22, 2026):

My bad for missing part of the announcement

Keep up the good work!

<!-- gh-comment-id:3786235038 --> @PaulMatthieu commented on GitHub (Jan 22, 2026): My bad for missing part of the announcement Keep up the good work!
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#71115
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?