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 #12143] How to disable low vram mode. or change the threshold to 8 GiB? #70131

New Issue
Closed
opened 2026-05-04 20:26:13 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 20:26:13 -05:00
Owner
Copy Link

Originally created by @aidemo2024 on GitHub (Sep 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12143

What is the issue?

i am using RTX 4070 SUPER (12 GB VRAM) in my PC, previously i am running ollama with deepseek-r1:8b, qwen3:4b, even gemma3:12b very smooth, after new update ollama, it become extreme slow. once i type ollama serve in cmd, i found a message msg="entering low vram mode" "total vram"="12.0 GiB" threshold="20.0 GiB" . How to disable low vram mode. or change the threshold to 8 GiB?

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.11.8

Originally created by @aidemo2024 on GitHub (Sep 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12143 ### What is the issue? i am using RTX 4070 SUPER (12 GB VRAM) in my PC, previously i am running ollama with deepseek-r1:8b, qwen3:4b, even gemma3:12b very smooth, after new update ollama, it become extreme slow. once i type ollama serve in cmd, i found a message msg="entering low vram mode" "total vram"="12.0 GiB" threshold="20.0 GiB" . How to disable low vram mode. or change the threshold to 8 GiB? ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.11.8
GiteaMirror added the question label 2026-05-04 20:26:13 -05:00
GiteaMirror commented 2026-05-04 20:26:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 1, 2025):

The only thing that low VRAM mode does (currently) is stop the server from setting a minimum context size of 8192 for the gpt-oss models. If you add server logs it will be easier to debug your problem.

<!-- gh-comment-id:3242462236 --> @rick-github commented on GitHub (Sep 1, 2025): The only thing that low VRAM mode does (currently) is stop the server from setting a minimum context size of 8192 for the gpt-oss models. If you add [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) it will be easier to debug your problem.
GiteaMirror commented 2026-05-04 20:26:22 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 2, 2025):

cc @jessegross

<!-- gh-comment-id:3247058498 --> @pdevine commented on GitHub (Sep 2, 2025): cc @jessegross
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 question
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#70131
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?