Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Vision Enabled Models #331

NotThePassword started this conversation in Ideas
Discussion options

First off, just want to say thank you for a great app! And the other thing I wanted to do was ask if you have thought about the models coming out with vision enabled and possibly added the ability to send images through the chat interface?

You must be logged in to vote

Replies: 2 comments 1 reply

Comment options

This has been requested many times, and it really just comes down to two issues:

  1. ChatterUI lacks any media storage. We will need to figure out how to attach media to the app cleanly.
  2. Vision models are very slow on mobile. Images are sent through an encoder which may not be supported by llama.rn and itself will take up about 200-300 tokens. Given the somewhat slow prefill speeds due to no NPU/GPU utilization, this makes running vision models non-viable, and honestly the results of said models are pretty poor due to their small sizes anyways.

I wont put it as a 'never add'. Models may get smarter and more efficient in the future, but its a 'not useful right now' situation.

You must be logged in to vote
1 reply
Comment options

Understood. Thank you for taking the time to respond.

Comment options

gemma 3n will be possible to run?

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Ideas
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /