github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13861] Flux2-Klein:4b won't create images | Error: 500 Internal Server Error: image runner exited unexpectedly: exit status 255 #34834

New Issue
Closed
opened 2026-04-22 18:45:19 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 18:45:19 -05:00
Owner
Copy Link

Originally created by @rebeccamice2002 on GitHub (Jan 23, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13861

What is the issue?

when i try to create any images, server giving me the error code 500 like this;

Error: 500 Internal Server Error: image runner exited unexpectedly: exit status 255

Relevant log output

$ ollama run x/flux2-klein "a cat holding a sign that says hello world"
pulling manifest 
writing manifest 
success 

Error: 500 Internal Server Error: image runner exited unexpectedly: exit status 255

and here is the server ouput

[GIN] 2026/01/23 - 16:11:48 | 500 |  6.534885666s |       127.0.0.1 | POST     "/api/generate"
time=2026-01-23T16:16:56.454+03:00 level=INFO source=server.go:149 msg="starting ollama-mlx image runner subprocess" exe=/usr/local/bin/ollama-mlx model=x/flux2-klein:4b port=39087
time=2026-01-23T16:16:56.539+03:00 level=INFO source=server.go:134 msg=image-runner msg="MLX error: cudaMallocManaged(&data_, small_pool_size) failed: CUDA driver version is insufficient for CUDA runtime version at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/random.cpp:143"
time=2026-01-23T16:16:56.571+03:00 level=INFO source=server.go:320 msg="stopping image runner subprocess" pid=302714

OS

Linux

GPU

Intel, Nvidia

CPU

Intel

Ollama version

0.14.2

Originally created by @rebeccamice2002 on GitHub (Jan 23, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13861 ### What is the issue? when i try to create any images, server giving me the error code 500 like this; Error: 500 Internal Server Error: image runner exited unexpectedly: exit status 255 ### Relevant log output ```shell $ ollama run x/flux2-klein "a cat holding a sign that says hello world" pulling manifest writing manifest success Error: 500 Internal Server Error: image runner exited unexpectedly: exit status 255 ``` and here is the server ouput ```shell [GIN] 2026/01/23 - 16:11:48 | 500 | 6.534885666s | 127.0.0.1 | POST "/api/generate" time=2026-01-23T16:16:56.454+03:00 level=INFO source=server.go:149 msg="starting ollama-mlx image runner subprocess" exe=/usr/local/bin/ollama-mlx model=x/flux2-klein:4b port=39087 time=2026-01-23T16:16:56.539+03:00 level=INFO source=server.go:134 msg=image-runner msg="MLX error: cudaMallocManaged(&data_, small_pool_size) failed: CUDA driver version is insufficient for CUDA runtime version at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/random.cpp:143" time=2026-01-23T16:16:56.571+03:00 level=INFO source=server.go:320 msg="stopping image runner subprocess" pid=302714 ``` ### OS Linux ### GPU Intel, Nvidia ### CPU Intel ### Ollama version 0.14.2
GiteaMirror added the bug label 2026-04-22 18:45:19 -05:00
GiteaMirror commented 2026-04-22 18:45:24 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 23, 2026):

CUDA driver version is insufficient for CUDA runtime version

Output of nvidia-smi?

<!-- gh-comment-id:3790324122 --> @rick-github commented on GitHub (Jan 23, 2026): ``` CUDA driver version is insufficient for CUDA runtime version ``` Output of `nvidia-smi`?
GiteaMirror commented 2026-04-22 18:45:26 -05:00
Author
Owner
Copy Link

@rebeccamice2002 commented on GitHub (Jan 23, 2026):

CUDA driver version is insufficient for CUDA runtime version

Output of nvidia-smi?

i actually cant use cuda with ollama bc i have 1050 ti which is an unsupported version of nvidia on ollamas cuda support

<!-- gh-comment-id:3790525442 --> @rebeccamice2002 commented on GitHub (Jan 23, 2026): > ``` > CUDA driver version is insufficient for CUDA runtime version > ``` > > Output of `nvidia-smi`? i actually cant use cuda with ollama bc i have 1050 ti which is an unsupported version of nvidia on ollamas cuda support
GiteaMirror commented 2026-04-22 18:45:26 -05:00
Author
Owner
Copy Link

@Antipula commented on GitHub (Jan 23, 2026):

MLX CUDA 12

<!-- gh-comment-id:3790604238 --> @Antipula commented on GitHub (Jan 23, 2026): MLX CUDA 12
GiteaMirror commented 2026-04-22 18:45:27 -05:00
Author
Owner
Copy Link

@stronk7 commented on GitHub (Jan 23, 2026):

Isn't the experimental image generation available only for Mac? I did read recently that the Windows / Linux compatibility was coming later.

I maybe wrong, but...

Ciao :-)

<!-- gh-comment-id:3791600590 --> @stronk7 commented on GitHub (Jan 23, 2026): Isn't the experimental image generation available only for Mac? I did read recently that the Windows / Linux compatibility was coming later. I maybe wrong, but... Ciao :-)
GiteaMirror commented 2026-04-22 18:45:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 23, 2026):

The release requires a bit of a fix up but can be made to work on Linux.

Image
<!-- gh-comment-id:3791722759 --> @rick-github commented on GitHub (Jan 23, 2026): The release requires a bit of a fix up but can be made to work on Linux. <img width="1020" height="1015" alt="Image" src="https://github.com/user-attachments/assets/fdc8c6b6-ad7e-4ec6-8515-824c1d99ab22" />
GiteaMirror commented 2026-04-22 18:45:29 -05:00
Author
Owner
Copy Link

@rebeccamice2002 commented on GitHub (Jan 23, 2026):

Isn't the experimental image generation available only for Mac? I did read recently that the Windows / Linux compatibility was coming later.

I maybe wrong, but...

Ciao :-)

oh.. i checked again and you are right. thank you for reminding that part.

<!-- gh-comment-id:3792621554 --> @rebeccamice2002 commented on GitHub (Jan 23, 2026): > Isn't the experimental image generation available only for Mac? I did read recently that the Windows / Linux compatibility was coming later. > > I maybe wrong, but... > > Ciao :-) oh.. i checked again and you are right. thank you for reminding that part.
GiteaMirror commented 2026-04-22 18:45:30 -05:00
Author
Owner
Copy Link

@madmax772 commented on GitHub (Jan 26, 2026):

[Incase this is helpful to speed up Linux support] I am hitting the same issue on Linux (Ubuntu) using an NVIDIA RTX 2000E Ada (16GB). I stopped all other services and verified I had ~16GB VRAM free before running the generation. The model loads successfully, but crashes immediately when encoding prompt with a dimension mismatch error in the MLX adapter. I can see Ollama "entering low vram mode" , but I don't think this is the culprit.

Logs:
Jan 26 08:18:17 ubuntu-desktop ollama[1283354]: time=2026-01-26T08:18:17.157-08:00 level=INFO source=server.go:129 msg=image-runner msg=" Encoding prompt... MLX error: [matmul] Last dimension of first input with shape (1,512,4096) must match second to last dimension of second input with shape (12288,4096). at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/ops.cpp:1943"

Environment:
OS: Ubuntu Linux
CPU: AMD
GPU: NVIDIA RTX 2000E Ada (16GB)
Ollama Version: 0.15.1
Model: x/flux2-klein:9b

<!-- gh-comment-id:3800550328 --> @madmax772 commented on GitHub (Jan 26, 2026): [Incase this is helpful to speed up Linux support] I am hitting the same issue on Linux (Ubuntu) using an NVIDIA RTX 2000E Ada (16GB). I stopped all other services and verified I had ~16GB VRAM free before running the generation. The model loads successfully, but crashes immediately when encoding prompt with a dimension mismatch error in the MLX adapter. I can see Ollama "entering low vram mode" , but I don't think this is the culprit. **Logs:** `Jan 26 08:18:17 ubuntu-desktop ollama[1283354]: time=2026-01-26T08:18:17.157-08:00 level=INFO source=server.go:129 msg=image-runner msg=" Encoding prompt... MLX error: [matmul] Last dimension of first input with shape (1,512,4096) must match second to last dimension of second input with shape (12288,4096). at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/ops.cpp:1943"` **Environment**: OS: Ubuntu Linux CPU: AMD GPU: NVIDIA RTX 2000E Ada (16GB) Ollama Version: 0.15.1 Model: x/flux2-klein:9b
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#34834
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?