Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Gemma3 supports vision, but the vision tag is not listed on the models page. #9694

Closed
LubyRuffy opened this issue Mar 12, 2025 · 6 comments
Closed
Assignees

Comments

@LubyRuffy
Copy link

LubyRuffy commented Mar 12, 2025

Thank you for your efforts, it's truly amazing!

Image

Image

@myNicole98
Copy link

This is a major issue for 3rd party integrations of ollama like Msty, as they think the model is not multimodal

Image

@BruceMacD
Copy link
Contributor

Hey everyone, I've got a fix for this queued up. Should be out soon.

@jofeltje2
Copy link

@BruceMacD Will it also support tool calling with ollama?

@BruceMacD
Copy link
Contributor

@jofeltje2 There is a tool calling template for gemma3, but my understanding is that it wasn't added to the ollama library Gemma upload as we could not get it to work consistently.

@BruceMacD
Copy link
Contributor

@myNicole98 for that case with the Msty UI, I think they will need to add a check like this to their code:

if len(info.ProjectorInfo) != 0 {

I plan on making this check easier soon, just got a few other code changes to get through first.

@BruceMacD
Copy link
Contributor

This is fixed now on ollama.com. Thanks for the report

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants