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 #6612] GPU Not Use #29925

New Issue
Closed
opened 2026-04-22 09:16:34 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 09:16:34 -05:00
Owner
Copy Link

Originally created by @MEnsar55 on GitHub (Sep 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6612

Originally assigned to: @dhiltgen on GitHub.

Hello, I am using Windows 11 and I have installed LLama3.1 7B and Gemma 2 27B in Ollama. When using these modems the GPU is between 0%-1%. What should I do?
My laptop specs are:
HP Victus
14700hx
4070
32 GB Ram

Originally created by @MEnsar55 on GitHub (Sep 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6612 Originally assigned to: @dhiltgen on GitHub. Hello, I am using Windows 11 and I have installed LLama3.1 7B and Gemma 2 27B in Ollama. When using these modems the GPU is between 0%-1%. What should I do? My laptop specs are: HP Victus 14700hx 4070 32 GB Ram
GiteaMirror added the nvidianeeds more infowindows labels 2026-04-22 09:16:34 -05:00
GiteaMirror commented 2026-04-22 09:16:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 3, 2024):

Server logs will help in debugging.

<!-- gh-comment-id:2327228011 --> @rick-github commented on GitHub (Sep 3, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will help in debugging.
GiteaMirror commented 2026-04-22 09:16:36 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 25, 2024):

There is no llama3.1 7B, but there is a 70B, and given you also mentioned gemma2 27B, I believe you're trying to load large models on a small VRAM system. Those two models are ~40G and ~16G respectively. I believe your GPU is an 8G card. Neither of these models will fit in VRAM, so they'll have to load mostly into system RAM and run on your CPU. Low GPU utilization in this case is expected, as the CPU is the bottleneck. Try loading smaller models that fit in your VRAM and you'll see much better performance. If you want the quality of these larger models, they will run slowly on your system.

<!-- gh-comment-id:2375386271 --> @dhiltgen commented on GitHub (Sep 25, 2024): There is no llama3.1 7B, but there is a 70B, and given you also mentioned gemma2 27B, I believe you're trying to load large models on a small VRAM system. Those two models are ~40G and ~16G respectively. I believe your GPU is an 8G card. Neither of these models will fit in VRAM, so they'll have to load mostly into system RAM and run on your CPU. Low GPU utilization in this case is expected, as the CPU is the bottleneck. Try loading smaller models that fit in your VRAM and you'll see much better performance. If you want the quality of these larger models, they will run slowly on your system.
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 needs more info nvidia windows
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#29925
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?