github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13845] x/flux2-klein:4b Error: insufficient memory for image generation: need 21 GB #55579

New Issue
Open
opened 2026-04-29 09:26:58 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-04-29 09:26:58 -05:00
Owner
Copy Link

Originally created by @dmitry-sukhoruchkin on GitHub (Jan 22, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13845

What is the issue?

ollama run x/flux2-klein:4b
pulling manifest
pulling model: 100% ▕█████████████████████████▏ 5.7 GB
writing manifest
success
Error: failed to load model: 500 Internal Server Error: image runner failed: Error: insufficient memory for image generation: need 21 GB, have 11 GB (exit: exit status 1)

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @dmitry-sukhoruchkin on GitHub (Jan 22, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13845 ### What is the issue? ollama run x/flux2-klein:4b pulling manifest pulling model: 100% ▕█████████████████████████▏ 5.7 GB writing manifest success Error: failed to load model: 500 Internal Server Error: image runner failed: Error: insufficient memory for image generation: need 21 GB, have 11 GB (exit: exit status 1) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the macosbug labels 2026-04-29 09:26:58 -05:00
GiteaMirror commented 2026-04-29 09:26:59 -05:00
Author
Owner
Copy Link

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

hey @dmitry-sukhoruchkin so sorry about this. Looking into this.

<!-- gh-comment-id:3786181989 --> @mchiang0610 commented on GitHub (Jan 22, 2026): hey @dmitry-sukhoruchkin so sorry about this. Looking into this.
GiteaMirror commented 2026-04-29 09:26:59 -05:00
Author
Owner
Copy Link

@SJTheGreat06 commented on GitHub (Jan 22, 2026):

I'm facing the same issue with my M4 MacBook Air. I'm looking forward to running image generation on my machine once it's been fixed

<!-- gh-comment-id:3786769010 --> @SJTheGreat06 commented on GitHub (Jan 22, 2026): I'm facing the same issue with my M4 MacBook Air. I'm looking forward to running image generation on my machine once it's been fixed
GiteaMirror commented 2026-04-29 09:27:00 -05:00
Author
Owner
Copy Link

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

I got the same error on Slackware Linux as others are describing for mac "need 21 GB"...

<!-- gh-comment-id:3787381088 --> @slackdesk commented on GitHub (Jan 22, 2026): I got the same error on Slackware Linux as others are describing for mac "need 21 GB"...
GiteaMirror commented 2026-04-29 09:27:00 -05:00
Author
Owner
Copy Link

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

same!

<!-- gh-comment-id:3789532088 --> @duatom commented on GitHub (Jan 23, 2026): same!
GiteaMirror commented 2026-04-29 09:27:00 -05:00
Author
Owner
Copy Link

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

same here

<!-- gh-comment-id:3789641922 --> @FuFusi commented on GitHub (Jan 23, 2026): same here
GiteaMirror commented 2026-04-29 09:27:00 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 24, 2026):

Should be fixed in 0.15.0.

<!-- gh-comment-id:3794368123 --> @rick-github commented on GitHub (Jan 24, 2026): Should be fixed in [0.15.0](https://github.com/ollama/ollama/releases/tag/v0.15.0).
GiteaMirror commented 2026-04-29 09:27:01 -05:00
Author
Owner
Copy Link

@SJTheGreat06 commented on GitHub (Jan 24, 2026):

Should be fixed in 0.15.0.

I can confirm that it's fixed! Thank you to the team for their swift and prompt action. Thank you very much!

<!-- gh-comment-id:3794537994 --> @SJTheGreat06 commented on GitHub (Jan 24, 2026): > Should be fixed in [0.15.0](https://github.com/ollama/ollama/releases/tag/v0.15.0). I can confirm that it's fixed! Thank you to the team for their swift and prompt action. Thank you very much!
GiteaMirror commented 2026-04-29 09:27:01 -05:00
Author
Owner
Copy Link

@mundotv789123 commented on GitHub (Jan 24, 2026):

I'm using a 5060 TI 16gb vram.
After updated to 0.15.0 a recived this error.

Error: 500 Internal Server Error: Post "http://127.0.0.1:42099/completion": EOF

logs:
time=2026-01-24T10:40:06.517-03:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=309.917819ms
time=2026-01-24T10:40:06.519-03:00 level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2026-01-24T10:40:06.519-03:00 level=DEBUG source=server.go:105 msg="mlx subprocess library path" LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/mlx_cuda_v13
time=2026-01-24T10:40:06.527-03:00 level=INFO source=server.go:143 msg="starting image runner subprocess" exe=/usr/local/bin/ollama model=x/flux2-klein:4b-fp8 port=44501
time=2026-01-24T10:40:06.902-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:87: INFO MLX library initialized"
time=2026-01-24T10:40:06.903-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:88: INFO starting image runner model=x/flux2-klein:4b-fp8 port=44501"
time=2026-01-24T10:40:06.907-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:92: INFO detected model type type=Flux2KleinPipeline"
time=2026-01-24T10:40:06.907-03:00 level=INFO source=server.go:129 msg=image-runner msg="Loading FLUX.2 Klein model from manifest: x/flux2-klein:4b-fp8..."
time=2026-01-24T10:40:07.327-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading tokenizer... ✓"
time=2026-01-24T10:40:12.640-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading text encoder... ✓"
time=2026-01-24T10:40:15.888-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading transformer... ✓"
time=2026-01-24T10:40:16.100-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading VAE... ✓"
time=2026-01-24T10:40:16.101-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Evaluating weights... ✓"
time=2026-01-24T10:40:16.101-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loaded in 9.19s (8.8 GB VRAM)"
time=2026-01-24T10:40:16.101-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:16 runner.go:139: INFO image runner listening addr=127.0.0.1:44501"
time=2026-01-24T10:40:16.128-03:00 level=INFO source=server.go:214 msg="image runner is ready" port=44501
time=2026-01-24T10:40:16.129-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Output: 1024x1024"
time=2026-01-24T10:40:16.144-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Encoding prompt... MLX error: [matmul] Last dimension of first input with shape (1,512,2560) must match second to last dimension of second input with shape (768,18432). at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/ops.cpp:1943"
[GIN] 2026/01/24 - 10:40:16 | 500 | 10.107061199s | 127.0.0.1 | POST "/api/generate"
time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096
time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096 duration=5m0s
time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096 refCount=0

<!-- gh-comment-id:3794644527 --> @mundotv789123 commented on GitHub (Jan 24, 2026): I'm using a 5060 TI 16gb vram. After updated to 0.15.0 a recived this error. Error: 500 Internal Server Error: Post "http://127.0.0.1:42099/completion": EOF logs: time=2026-01-24T10:40:06.517-03:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=309.917819ms time=2026-01-24T10:40:06.519-03:00 level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 time=2026-01-24T10:40:06.519-03:00 level=DEBUG source=server.go:105 msg="mlx subprocess library path" LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/mlx_cuda_v13 time=2026-01-24T10:40:06.527-03:00 level=INFO source=server.go:143 msg="starting image runner subprocess" exe=/usr/local/bin/ollama model=x/flux2-klein:4b-fp8 port=44501 time=2026-01-24T10:40:06.902-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:87: INFO MLX library initialized" time=2026-01-24T10:40:06.903-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:88: INFO starting image runner model=x/flux2-klein:4b-fp8 port=44501" time=2026-01-24T10:40:06.907-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:06 runner.go:92: INFO detected model type type=Flux2KleinPipeline" time=2026-01-24T10:40:06.907-03:00 level=INFO source=server.go:129 msg=image-runner msg="Loading FLUX.2 Klein model from manifest: x/flux2-klein:4b-fp8..." time=2026-01-24T10:40:07.327-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading tokenizer... ✓" time=2026-01-24T10:40:12.640-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading text encoder... ✓" time=2026-01-24T10:40:15.888-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading transformer... ✓" time=2026-01-24T10:40:16.100-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loading VAE... ✓" time=2026-01-24T10:40:16.101-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Evaluating weights... ✓" time=2026-01-24T10:40:16.101-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Loaded in 9.19s (8.8 GB VRAM)" time=2026-01-24T10:40:16.101-03:00 level=WARN source=server.go:136 msg=image-runner msg="2026/01/24 10:40:16 runner.go:139: INFO image runner listening addr=127.0.0.1:44501" time=2026-01-24T10:40:16.128-03:00 level=INFO source=server.go:214 msg="image runner is ready" port=44501 time=2026-01-24T10:40:16.129-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Output: 1024x1024" time=2026-01-24T10:40:16.144-03:00 level=INFO source=server.go:129 msg=image-runner msg=" Encoding prompt... MLX error: [matmul] Last dimension of first input with shape (1,512,2560) must match second to last dimension of second input with shape (768,18432). at /go/src/github.com/ollama/ollama/build/_deps/mlx-c-src/mlx/c/ops.cpp:1943" [GIN] 2026/01/24 - 10:40:16 | 500 | 10.107061199s | 127.0.0.1 | POST "/api/generate" time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:394 msg="context for request finished" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096 time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:299 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096 duration=5m0s time=2026-01-24T10:40:16.163-03:00 level=DEBUG source=sched.go:317 msg="after processing request finished event" runner.name=registry.ollama.ai/x/flux2-klein:4b-fp8 runner.size="8.8 GiB" runner.vram="8.8 GiB" runner.parallel=0 runner.pid=0 runner.model="" runner.num_ctx=4096 refCount=0
GiteaMirror commented 2026-04-29 09:27:01 -05:00
Author
Owner
Copy Link

@Acharab commented on GitHub (Jan 24, 2026):

Got the same error Error: 500 Internal Server Error: Post "http://127.0.0.1:34967/completion": EOF

<!-- gh-comment-id:3794803589 --> @Acharab commented on GitHub (Jan 24, 2026): Got the same error Error: 500 Internal Server Error: Post "http://127.0.0.1:34967/completion": EOF
GiteaMirror commented 2026-04-29 09:27:01 -05:00
Author
Owner
Copy Link

@SJTheGreat06 commented on GitHub (Jan 24, 2026):

I'm using a 5060 TI 16gb vram.
After updated to 0.15.0 a recived this error.

As of now, image generation is only supported on MacOS, not Windows or Linux

<!-- gh-comment-id:3795202724 --> @SJTheGreat06 commented on GitHub (Jan 24, 2026): > I'm using a 5060 TI 16gb vram. > After updated to 0.15.0 a recived this error. As of now, image generation is only supported on MacOS, not Windows or Linux
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 macos
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#55579
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?