[GH-ISSUE #4644] more types of models #64955

Closed
opened 2026-05-03 19:24:31 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @zsq2010 on GitHub (May 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4644

could we have more type of modles like,vision model,tts,ocr,etc

Originally created by @zsq2010 on GitHub (May 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4644 could we have more type of modles like,vision model,tts,ocr,etc
GiteaMirror added the feature request label 2026-05-03 19:24:31 -05:00
Author
Owner

@dhiltgen commented on GitHub (Jul 25, 2024):

Lets track these with discrete issues since these will be supported with different models.

Some vision models are already supported like llava and blakllava If there are other vision models we don't yet support you'd like to see, please submit model requests for them.

Voice/speach is tracked via #1168

For OCR, llava 1.6 is claimed to have better OCR performance, and is available. If there are other specific models for OCR you'd like to see please submit model requests for those.

<!-- gh-comment-id:2251561857 --> @dhiltgen commented on GitHub (Jul 25, 2024): Lets track these with discrete issues since these will be supported with different models. Some vision models are already supported like [llava](https://ollama.com/library/llava) and [blakllava](https://ollama.com/library/bakllava) If there are other vision models we don't yet support you'd like to see, please submit model requests for them. Voice/speach is tracked via #1168 For OCR, llava 1.6 is claimed to have better OCR performance, and is available. If there are other specific models for OCR you'd like to see please submit model requests for those.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#64955