github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11953] Drews54/llama3.2-vision-abliterated: 'llama3.2-vision' is no longer compatible with your version of Ollama #7936

New Issue
Open
opened 2026-04-12 20:06:07 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 20:06:07 -05:00
Owner
Copy Link

Originally created by @jferments on GitHub (Aug 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11953

What is the issue?

What happened:

When I attempt to run the model Drews54/llama3.2-vision-abliterated with the latest version of ollama I get the following error:

jferments@ML:~/code/captioning$ ollama run Drews54/llama3.2-vision-abliterated 
Error: 500 Internal Server Error: 'llama3.2-vision' is no longer compatible with your version of Ollama and has been replaced by a newer version. To re-download, run 'ollama pull llama3.2-vision'

What I expected to happen:

The model, which is listed on the official models page, should run successfully.

Relevant log output

OS

Ubuntu 24.04.2 LTS

GPU

2 x RTX 4090

CPU

AMD7965WX

Ollama version

0.11.4

Originally created by @jferments on GitHub (Aug 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11953 ### What is the issue? ### What happened: When I attempt to run the model Drews54/llama3.2-vision-abliterated with the latest version of ollama I get the following error: ``` jferments@ML:~/code/captioning$ ollama run Drews54/llama3.2-vision-abliterated Error: 500 Internal Server Error: 'llama3.2-vision' is no longer compatible with your version of Ollama and has been replaced by a newer version. To re-download, run 'ollama pull llama3.2-vision' ``` ### What I expected to happen: The model, which is listed on the official models page, should run successfully. ### Relevant log output ```shell ``` ### OS Ubuntu 24.04.2 LTS ### GPU 2 x RTX 4090 ### CPU AMD7965WX ### Ollama version 0.11.4
GiteaMirror added the bug label 2026-04-12 20:06:07 -05:00
GiteaMirror commented 2026-04-12 20:06:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 18, 2025):

Drews54/llama3.2-vision-abliterated is not an official model, it has been uploaded by a user. It uses the split GGUF method (seperate projector and text weights) which is not supported in the new ollama engine.

<!-- gh-comment-id:3196021592 --> @rick-github commented on GitHub (Aug 18, 2025): Drews54/llama3.2-vision-abliterated is not an official model, it has been uploaded by a user. It uses the split GGUF method (seperate projector and text weights) which is not supported in the new ollama engine.
GiteaMirror commented 2026-04-12 20:06:10 -05:00
Author
Owner
Copy Link

@Justinius commented on GitHub (Aug 18, 2025):

If he sets OLLAMA_NEW_ENGINE to FALSE, would it still run?

ollama/llm/server.go still seems to have a fall back path, but if its getting this error it seems like it might not be working, or when checking for required architecture this specific model is reporting one of the ones in ollama/fs/ggml/ggml.go

<!-- gh-comment-id:3197551732 --> @Justinius commented on GitHub (Aug 18, 2025): If he sets OLLAMA_NEW_ENGINE to FALSE, would it still run? ollama/llm/server.go still seems to have a fall back path, but if its getting this error it seems like it might not be working, or when checking for required architecture this specific model is reporting one of the ones in ollama/fs/ggml/ggml.go
GiteaMirror commented 2026-04-12 20:06:10 -05:00
Author
Owner
Copy Link

@adityamatt commented on GitHub (Aug 27, 2025):

+1 , having the same issue

<!-- gh-comment-id:3229852061 --> @adityamatt commented on GitHub (Aug 27, 2025): +1 , having the same issue
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#7936
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?