[GH-ISSUE #6438] LlaVA OneVision #29808

Open
opened 2026-04-22 09:03:59 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @ddpasa on GitHub (Aug 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6438

Promising multimodal model: https://huggingface.co/collections/lmms-lab/llava-onevision-66a259c3526e15166d6bba37

llama.cpp issue: https://github.com/ggerganov/llama.cpp/issues/8944

Originally created by @ddpasa on GitHub (Aug 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6438 Promising multimodal model: https://huggingface.co/collections/lmms-lab/llava-onevision-66a259c3526e15166d6bba37 llama.cpp issue: https://github.com/ggerganov/llama.cpp/issues/8944
GiteaMirror added the model label 2026-04-22 09:03:59 -05:00
Author
Owner

@silasalves commented on GitHub (Sep 6, 2024):

@ddpasa Model already requested in #6255

I think all models that use video input do not work properly with Ollama at the moment (see https://github.com/ollama/ollama/issues/3184#issuecomment-2259137049).

<!-- gh-comment-id:2334779391 --> @silasalves commented on GitHub (Sep 6, 2024): @ddpasa Model already requested in #6255 I think all models that use video input do not work properly with Ollama at the moment (see https://github.com/ollama/ollama/issues/3184#issuecomment-2259137049).
Author
Owner

@mihow commented on GitHub (Dec 4, 2024):

Can you implement OneVision in Ollama without video support? Just a single or the multi image input?

<!-- gh-comment-id:2516533300 --> @mihow commented on GitHub (Dec 4, 2024): Can you implement OneVision in Ollama without video support? Just a single or the multi image input?
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#29808