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 #12243] 20GB VRAM threshold hard coded? Low VRAM mode with 16GB VRAM #33905

New Issue
Closed
opened 2026-04-22 17:05:23 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 17:05:23 -05:00
Owner
Copy Link

Originally created by @rico666 on GitHub (Sep 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12243

What is the issue?

My GPU 16GB VRAM RTX5000 is not used because of low vram mode?

I'm unable to modify the threshold which seems to be hard set to 20GB. Is that the everyday casual VRAM size today?

hard enough to get a notebook with 16GB VRAM...

Relevant log output

time=2025-09-10T22:02:49.002+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d6d498ce-8dc3-cf77-af3c-ad6db192314e library=cuda variant=v12 compute=7.5 driver=13.0 name="Quadro RTX 5000" total="15.6 GiB" available="15.4 GiB"
time=2025-09-10T22:02:49.002+02:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.6 GiB" threshold="20.0 GiB"

OS

Arch Linux

GPU

Nvidia Quadro RTX5000 (Turing) 16GB VRAM

CPU

Xeon 2276M

Ollama version

0.11.8

Originally created by @rico666 on GitHub (Sep 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12243 ### What is the issue? My GPU 16GB VRAM RTX5000 is not used because of low vram mode? I'm unable to modify the threshold which seems to be hard set to 20GB. Is that the everyday casual VRAM size today? hard enough to get a notebook with 16GB VRAM... ### Relevant log output ```shell time=2025-09-10T22:02:49.002+02:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d6d498ce-8dc3-cf77-af3c-ad6db192314e library=cuda variant=v12 compute=7.5 driver=13.0 name="Quadro RTX 5000" total="15.6 GiB" available="15.4 GiB" time=2025-09-10T22:02:49.002+02:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.6 GiB" threshold="20.0 GiB" ``` ### OS Arch Linux ### GPU Nvidia Quadro RTX5000 (Turing) 16GB VRAM ### CPU Xeon 2276M ### Ollama version 0.11.8
GiteaMirror added the bug label 2026-04-22 17:05:23 -05:00
GiteaMirror commented 2026-04-22 17:05:25 -05:00
Author
Owner
Copy Link

@rico666 commented on GitHub (Sep 11, 2025):

I have read #12143 - this issue can be closed, but the problem experienced is a different one: Ollama packaged by Arch Linux has no GPU support! According to https://itnext.io/ai-introduction-to-ollama-for-local-llm-launch-a95e5200c3e7

I can confirm that ollama installed via pacman - no chance to get GPU going, which is especially problematic when ollama logs these GPU-related messages. So if there is a compile option to remove GPU, then maybe state so in the log "No GPU support" or somesuch.

ollama installed via curl -fsSL https://ollama.com/install.sh | sh - no problem so far.

<!-- gh-comment-id:3281241855 --> @rico666 commented on GitHub (Sep 11, 2025): I have read #12143 - this issue can be closed, but the problem experienced is a different one: Ollama packaged by Arch Linux has no GPU support! According to https://itnext.io/ai-introduction-to-ollama-for-local-llm-launch-a95e5200c3e7 I can confirm that ollama installed via pacman - no chance to get GPU going, which is especially problematic when ollama logs these GPU-related messages. So if there is a compile option to remove GPU, then maybe state so in the log "No GPU support" or somesuch. ollama installed via `curl -fsSL https://ollama.com/install.sh | sh` - no problem so far.
GiteaMirror commented 2026-04-22 17:05:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 11, 2025):

Install ollama-cuda.

https://wiki.archlinux.org/title/Ollama

Image
<!-- gh-comment-id:3281282189 --> @rick-github commented on GitHub (Sep 11, 2025): Install ollama-cuda. https://wiki.archlinux.org/title/Ollama <img width="703" height="399" alt="Image" src="https://github.com/user-attachments/assets/6ea1da78-ccaa-4910-a57e-7e8cc6488612" />
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 bug
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#33905
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?