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 #14002] CPU > gpt-oss:latest vs GPU > llama3.1:latest, Ollama w/ Open WebUI #55665

New Issue
Closed
opened 2026-04-29 09:33:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 09:33:31 -05:00
Owner
Copy Link

Originally created by @jekv2 on GitHub (Jan 31, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14002

I been asking some stuff on both models in Ollama through Open WebUI.

I noticed that CPU Intensive > gpt-oss:latest. GPU Intensive> llama3.1:latest, Ollama w/ Open WebUI.

I understand that AI is render intensive, my question is, why is gpt-oss is using my CPU "9950x" Rather my "3090TIFE"?
llama uses my GPU.

Is there a way to change this for gpt-oss in Open WebUI?

As I cannot access the settings to Ollama from windows10 tray icon. Does not open as described here https://github.com/ollama/ollama/issues/14000

Originally created by @jekv2 on GitHub (Jan 31, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14002 I been asking some stuff on both models in Ollama through Open WebUI. I noticed that CPU Intensive > gpt-oss:latest. GPU Intensive> llama3.1:latest, Ollama w/ Open WebUI. I understand that AI is render intensive, my question is, why is gpt-oss is using my CPU "9950x" Rather my "3090TIFE"? llama uses my GPU. Is there a way to change this for gpt-oss in Open WebUI? As I cannot access the settings to Ollama from windows10 tray icon. Does not open as described here https://github.com/ollama/ollama/issues/14000
GiteaMirror commented 2026-04-29 09:33:32 -05:00
Author
Owner
Copy Link

@winstonma commented on GitHub (Jan 31, 2026):

llama3.1:latest is a 4.9GB model while gpt-oss:latest is a 14GB model.

Could you also list which GPU you’re using and how much memory it has?

<!-- gh-comment-id:3829640357 --> @winstonma commented on GitHub (Jan 31, 2026): [llama3.1:latest](https://ollama.com/library/llama3.1) is a 4.9GB model while [gpt-oss:latest](https://ollama.com/library/gpt-oss) is a 14GB model. Could you also list which GPU you’re using and how much memory it has?
GiteaMirror commented 2026-04-29 09:33:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 1, 2026):

time=2026-01-31T15:21:10.646-06:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-31f97312-c981-417d-08bd-00e35abe8dd1 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 Ti" libdirs=ollama,cuda_v13 driver=13.1 pci_id=0000:01:00.0 type=discrete total="8.0 GiB" available="7.5 GiB"

You have 7.5GiB VRAM available. As winstonma has pointed out, the two models are very different in size. The 14G gpt-oss will not fit in the GPU VRAM, so part of the model is loaded in system RAM where the CPU does inference. If you run ollama ps when gpt-oss is loaded it will show the percentage of model running in CPU and GPU.

<!-- gh-comment-id:3831324757 --> @rick-github commented on GitHub (Feb 1, 2026): ``` time=2026-01-31T15:21:10.646-06:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-31f97312-c981-417d-08bd-00e35abe8dd1 filter_id="" library=CUDA compute=8.6 name=CUDA0 description="NVIDIA GeForce RTX 3060 Ti" libdirs=ollama,cuda_v13 driver=13.1 pci_id=0000:01:00.0 type=discrete total="8.0 GiB" available="7.5 GiB" ``` You have 7.5GiB VRAM available. As winstonma has pointed out, the two models are very different in size. The 14G gpt-oss will not fit in the GPU VRAM, so part of the model is loaded in system RAM where the CPU does inference. If you run `ollama ps` when gpt-oss is loaded it will show the percentage of model running in CPU and GPU.
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#55665
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?