github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13985] Gemma3 add support for do_pan_and_scan #9145

New Issue
Open
opened 2026-04-12 21:59:48 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:59:48 -05:00
Owner
Copy Link

Originally created by @dempo93 on GitHub (Jan 30, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13985

Fundamentally reopens #10392.
Gemma3 offers native dynamic resolution support via tiling (do_pan_and_scan flag) but this seems not to be implemented in ollama.

I tried to extract data points from a bunch of high resolution engineering drawings using gemma3 via ollama and I obtained a very low accuracy (around 30% on my benchmark, with extensive hallucinations). Then I tried externally replicating gemma's pan and scan functionality with python, slicing the high resolution images into 892x892 pixel tiles and then passing them into the context. The accuracy then climbed up to roughly 65%, on par with qwen2.5-vl:72b (which kind of matched my expectations)

Is it possible to enable pan and scan natively in ollama?

Originally created by @dempo93 on GitHub (Jan 30, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13985 Fundamentally reopens #10392. Gemma3 offers native dynamic resolution support via tiling (`do_pan_and_scan` flag) but this seems not to be implemented in ollama. I tried to extract data points from a bunch of high resolution engineering drawings using gemma3 via ollama and I obtained a very low accuracy (around 30% on my benchmark, with extensive hallucinations). Then I tried externally replicating gemma's pan and scan functionality with python, slicing the high resolution images into 892x892 pixel tiles and then passing them into the context. The accuracy then climbed up to roughly 65%, on par with qwen2.5-vl:72b (which kind of matched my expectations) Is it possible to enable pan and scan natively in ollama?
GiteaMirror added the feature request label 2026-04-12 21:59:48 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9145
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?