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 #14988] is there something wrong with the models folder setting #9634

New Issue
Open
opened 2026-04-12 22:31:51 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 22:31:51 -05:00
Owner
Copy Link

Originally created by @cdll on GitHub (Mar 21, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14988

What is the issue?

I recently found that on my Windows, ollama.exe loads my models into 100% CPU, and ollama serve which is from cli, load my models as 60%/40% CPU/GPU, and another deferent thing is that i 've already pulled 6 models which ollama.exe put them into the folder D:\.ollama\models\ that i set in ollama.exe's setting, but in the situation that ollama serve runs ollama ls, then i see only 2 models listing and i found the 2 models refers to the default model folder at C:\Users\Me\.ollama\models\. i wonder why and i was trying to figure out why the model could loads into parts of GPU and parts of CPU with command line ollama serve and ollama run <model>, but the model loads into fully CPU with ollama.exe which is evry slowly loading and responsing 🤣.

Relevant log output

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.18.2

Originally created by @cdll on GitHub (Mar 21, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14988 ### What is the issue? I recently found that on my Windows, ollama.exe loads my models into `100% CPU`, and `ollama serve` which is from cli, load my models as `60%/40% CPU/GPU`, and another deferent thing is that i 've already pulled 6 models which ollama.exe put them into the folder `D:\.ollama\models\` that i set in ollama.exe's setting, but in the situation that `ollama serve` runs `ollama ls`, then i see only 2 models listing and i found the 2 models refers to the default model folder at ` C:\Users\Me\.ollama\models\`. i wonder why and i was trying to figure out why the model could loads into parts of GPU and parts of CPU with command line `ollama serve` and `ollama run <model>`, but the model loads into fully CPU with `ollama.exe` which is evry slowly loading and responsing 🤣. ### Relevant log output ```shell ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.18.2
GiteaMirror added the bug label 2026-04-12 22:31:51 -05:00
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#9634
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?