github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14366] Ollama / Openclaw / Hostinger KVM 8 - Pegs the server #71395

New Issue
Closed
opened 2026-05-05 01:29:05 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-05 01:29:05 -05:00
Owner
Copy Link

Originally created by @santonivich on GitHub (Feb 23, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14366

Image

That's me using qwen2.5:3b-instruct on Openclaw hosted on a KVM 2 connecting to my ollama on a KVM 8. The specs of the dedicated ollama server are:

CPU core 8
Memory 32 GB
Disk space 400 GB

Grated, I realize that I need more power in reality...but...no matter what model I am using the server just gets destroyed. Has anyone dealt with this and got it working or am I simply dealing with a ollama server that doesn't have the horsepower?

Thanks

Originally created by @santonivich on GitHub (Feb 23, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14366 <img width="1906" height="202" alt="Image" src="https://github.com/user-attachments/assets/5d3d8ee7-9e6d-40c1-8260-6734261b8d92" /> That's me using qwen2.5:3b-instruct on Openclaw hosted on a KVM 2 connecting to my ollama on a KVM 8. The specs of the dedicated ollama server are: CPU core 8 Memory 32 GB Disk space 400 GB Grated, I realize that I need more power in reality...but...no matter what model I am using the server just gets destroyed. Has anyone dealt with this and got it working or am I simply dealing with a ollama server that doesn't have the horsepower? Thanks
GiteaMirror added the question label 2026-05-05 01:29:05 -05:00
GiteaMirror commented 2026-05-05 01:29:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 23, 2026):

Not enough horsepower. You can reduce the amount of CPU that the model consumes by limiting the number of threads it can use:

$ ollama run qwen2.5:3b-instruct-q4_K_M
>>> /set parameter num_thread 4
Set parameter 'num_thread' to '4'
>>> /save qwen2.5:3b-4t             
Created new model 'qwen2.5:3b-4t'
>>> 
$ ollama run qwen2.5:3b-4t

This will run slower but won't hammer your box as much.

<!-- gh-comment-id:3942059588 --> @rick-github commented on GitHub (Feb 23, 2026): Not enough horsepower. You can reduce the amount of CPU that the model consumes by limiting the number of threads it can use: ```console $ ollama run qwen2.5:3b-instruct-q4_K_M >>> /set parameter num_thread 4 Set parameter 'num_thread' to '4' >>> /save qwen2.5:3b-4t Created new model 'qwen2.5:3b-4t' >>> $ ollama run qwen2.5:3b-4t ``` This will run slower but won't hammer your box as much.
GiteaMirror commented 2026-05-05 01:29:11 -05:00
Author
Owner
Copy Link

@santonivich commented on GitHub (Feb 23, 2026):

Thanks. That’s what I figured the issue was. I appreciate confirming.

<!-- gh-comment-id:3942066549 --> @santonivich commented on GitHub (Feb 23, 2026): Thanks. That’s what I figured the issue was. I appreciate confirming.
GiteaMirror commented 2026-05-05 01:29:14 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 23, 2026):

If available, a GPU will result in a marked increase in performance.

<!-- gh-comment-id:3942070211 --> @rick-github commented on GitHub (Feb 23, 2026): If available, a GPU will result in a marked increase in performance.
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#71395
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?