github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10889] Option to not offload vision to GPU #53670

New Issue
Open
opened 2026-04-29 04:27:03 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 04:27:03 -05:00
Owner
Copy Link

Originally created by @weikinhuang on GitHub (May 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10889

Hi, I'm wondering if there are any plans for ollama to support skipping offload for both the old and new engines for the projectors. I'm currently using mistral 3.1 small, prior to the version that ollama added vision support, I was able to fit 95% of the model in VRAM, however with the latest updates with the vision projector taking ~8G of VRAM, the model has become unusably slow.

I'm currently testing out llama.cpp's --no-mmproj-offload option and it's working pretty well for mistral, it would be great to add similar functionality to ollama's engine.

Originally created by @weikinhuang on GitHub (May 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10889 Hi, I'm wondering if there are any plans for ollama to support skipping offload for both the old and new engines for the projectors. I'm currently using mistral 3.1 small, prior to the version that ollama added vision support, I was able to fit 95% of the model in VRAM, however with the latest updates with the vision projector taking ~8G of VRAM, the model has become unusably slow. I'm currently testing out llama.cpp's `--no-mmproj-offload` option and it's working pretty well for mistral, it would be great to add similar functionality to ollama's engine.
GiteaMirror added the feature request label 2026-04-29 04:27:03 -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#53670
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?