github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1742] Low VRAM mode? #47508

New Issue
Closed
opened 2026-04-28 04:03:08 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 04:03:08 -05:00
Owner
Copy Link

Originally created by @JumboTortoise on GitHub (Dec 30, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1742

I have a 12GB RTX 3060 that can easily run 7B models, but fails on the larger ones. Does ollama have a low-vram mode? Any way to move model layers from VRAM to system RAM? I would really like to try out larger LLM's without having to rent a cloud compute server or buy a new GPU, even if it is much slower due to inference optimizations.

I am not very knowledgeable on the subject, but maybe using DeepSpeed for boosting inference performance is a possibility?

Originally created by @JumboTortoise on GitHub (Dec 30, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1742 I have a 12GB RTX 3060 that can easily run 7B models, but fails on the larger ones. Does ollama have a low-vram mode? Any way to move model layers from VRAM to system RAM? I would really like to try out larger LLM's without having to rent a cloud compute server or buy a new GPU, even if it is much slower due to inference optimizations. I am not very knowledgeable on the subject, but maybe using DeepSpeed for boosting inference performance is a possibility?
GiteaMirror commented 2026-04-28 04:03:10 -05:00
Author
Owner
Copy Link

@DrGood01 commented on GitHub (Dec 30, 2023):

#1727

<!-- gh-comment-id:1872500991 --> @DrGood01 commented on GitHub (Dec 30, 2023): #1727
GiteaMirror commented 2026-04-28 04:03:11 -05:00
Author
Owner
Copy Link

@JumboTortoise commented on GitHub (Dec 30, 2023):

Thanks, I saw this issue in the tracker but didn't understand it was what I was searching for.

<!-- gh-comment-id:1872507547 --> @JumboTortoise commented on GitHub (Dec 30, 2023): Thanks, I saw this issue in the tracker but didn't understand it was what I was searching for.
GiteaMirror commented 2026-04-28 04:03:11 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Jan 2, 2024):

Ollama automatically spills models into system RAM, except when it doesn't work properly. I don't know why it sometimes doesn't work properly. I suspect it may be an issue with models that have larger context sizes, but I don't have a PC with NVIDIA, so I can't test it for myself.

<!-- gh-comment-id:1874575213 --> @easp commented on GitHub (Jan 2, 2024): Ollama automatically spills models into system RAM, except when it doesn't work properly. I don't know why it sometimes doesn't work properly. I suspect it may be an issue with models that have larger context sizes, but I don't have a PC with NVIDIA, so I can't test it for myself.
GiteaMirror commented 2026-04-28 04:03:11 -05:00
Author
Owner
Copy Link

@kilitary commented on GitHub (Jul 3, 2024):

also if you have integrated video card, you have memory shared with cpu and belong to all system memory

<!-- gh-comment-id:2206929232 --> @kilitary commented on GitHub (Jul 3, 2024): also if you have integrated video card, you have memory shared with cpu and belong to all system memory
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
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#47508
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?