github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3806] sustained beep during inference with any model #2351

New Issue
Closed
opened 2026-04-12 12:40:17 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:40:17 -05:00
Owner
Copy Link

Originally created by @matt453 on GitHub (Apr 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3806

What is the issue?

I am getting a sustained beep from my motherboard every time I am doing inference with an ollama model while asking questions from a command line shell. the inference happens near instantly but I am not sure what is causing the beeping.

I have tried running a few models
llama2:latest
llama3:8b-instruct-fp16

In either case I see the model successfully load into VRAM on my graphics card and can see activity on the GPU using things like nvtop nvitop and nividia-smi

the other thing I notice is that the ollama serve process always begins to use 100% of one CPU during this inference and the beeping.

I have confirmed my fans are all running both in my case, on the cpu and on the nvidia GPU, and the GPU temperature never goes above 40C - 50C. The CPU temp gets into the 60C -70C during these windows.

I have tried other things to stress the CPU or regular RAM (using stress) and nothing else triggers this beeping, even with higher CPU temperatures. any ideas what is unique to running ollama that could cause this?

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.1.30

Originally created by @matt453 on GitHub (Apr 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3806 ### What is the issue? I am getting a sustained beep from my motherboard every time I am doing inference with an ollama model while asking questions from a command line shell. the inference happens near instantly but I am not sure what is causing the beeping. I have tried running a few models `llama2:latest` `llama3:8b-instruct-fp16` In either case I see the model successfully load into VRAM on my graphics card and can see activity on the GPU using things like `nvtop` `nvitop` and `nividia-smi` the other thing I notice is that the `ollama serve` process always begins to use 100% of one CPU during this inference and the beeping. I have confirmed my fans are all running both in my case, on the cpu and on the nvidia GPU, and the GPU temperature never goes above 40C - 50C. The CPU temp gets into the 60C -70C during these windows. I have tried other things to stress the CPU or regular RAM (using `stress`) and nothing else triggers this beeping, even with higher CPU temperatures. any ideas what is unique to running ollama that could cause this? ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.30
GiteaMirror added the bug label 2026-04-12 12:40:17 -05:00
GiteaMirror commented 2026-04-12 12:40:18 -05:00
Author
Owner
Copy Link

@matt453 commented on GitHub (Apr 21, 2024):

I take it all back. it looks like it was my backup power supply that was beeping when I had high power usage. the power supply and the PC case were very close together.. so I am all good. closing the issue

<!-- gh-comment-id:2068228618 --> @matt453 commented on GitHub (Apr 21, 2024): I take it all back. it looks like it was my backup power supply that was beeping when I had high power usage. the power supply and the PC case were very close together.. so I am all good. closing the issue
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#2351
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?