Images and context windows #296

Open
opened 2026-02-15 16:29:42 -05:00 by yindo · 0 comments
Owner

Originally created by @Ale-Ceck on GitHub (Sep 15, 2025).

I'm trying to use multimodal models in order to analyze some pdfs files.
I want to know how the images impact on the context window: pdfs are long and having one image per page i wanted to know what's the maximum number of page i can analyze per query. I read that images don't afflict context window directly, but I can't figure out how they are managed in order to be used by the models.

Originally created by @Ale-Ceck on GitHub (Sep 15, 2025). I'm trying to use multimodal models in order to analyze some pdfs files. I want to know how the images impact on the context window: pdfs are long and having one image per page i wanted to know what's the maximum number of page i can analyze per query. I read that images don't afflict context window directly, but I can't figure out how they are managed in order to be used by the models.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ollama/ollama-python#296