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 #10519] Gemma3 Vision conversion from gguf #53434

New Issue
Closed
opened 2026-04-29 03:09:21 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 03:09:21 -05:00
Owner
Copy Link

Originally created by @mmathew23 on GitHub (May 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10519

What is the issue?

In general, when people finetune vision models they can use the llama.cpp script to convert to gguf files, create a modelfile and then create an ollama model. This is an extremely common workflow, especially for custom quants. At the moment there is no way to programmatically do this for gemma3 vision models as it uses a different format requiring a single gguf. @pdevine mentioned stitching together the ggufs to follow the ollama format. I'm able to do this but ollama create fails but a fix is suggested at #10162. A common question we get at unsloth is how to run these vision finetunes with ollama and we'd love to be able to help with that. Accepting #10162 would unblock us. Alternatively, could ollama provide some guidance or thoughts for the plan to suport vision models going forward.

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @mmathew23 on GitHub (May 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10519 ### What is the issue? In general, when people finetune vision models they can use the llama.cpp script to convert to gguf files, create a modelfile and then create an ollama model. This is an extremely common workflow, especially for custom quants. At the moment there is no way to programmatically do this for gemma3 vision models as it uses a different format requiring a single gguf. @pdevine mentioned stitching together the ggufs to follow the ollama format. I'm able to do this but ollama create fails but a fix is suggested at [#10162](https://github.com/ollama/ollama/pull/10162). A common question we get at unsloth is how to run these vision finetunes with ollama and we'd love to be able to help with that. Accepting #10162 would unblock us. Alternatively, could ollama provide some guidance or thoughts for the plan to suport vision models going forward. ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the questionbug labels 2026-04-29 03:09:30 -05:00
GiteaMirror commented 2026-04-29 03:09:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

Fixed by #10722

<!-- gh-comment-id:2899277828 --> @rick-github commented on GitHub (May 21, 2025): Fixed by #10722
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 question
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#53434
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?