github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5508] Ollama running 2 instances #65480

New Issue
Closed
opened 2026-05-03 21:27:07 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 21:27:07 -05:00
Owner
Copy Link

Originally created by @electro199 on GitHub (Jul 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5508

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

When starting ollama from start menu tray it starts the service for ollama which immediately loads model under name ollama.exe using around 4.5 GB ram and when using api it starts another program called ollama_llama_server.exe using around 4 GB of ram and almost 3 GB of vram.

The main issue is when ollama starts it should be the olllama_server loading the model not the olllama.exe

In this screenshot i was using ollama through api and i click on ollama then loads the model along side but ignoring the already running server
Screenshot 2024-07-06 014823

I am not sure if it is intended behavior or not, also how do I stop ollama from loading the model at startup without turning off the service.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.48

Originally created by @electro199 on GitHub (Jul 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5508 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? When starting ollama from start menu tray it starts the service for ollama which immediately loads model under name ollama.exe using around 4.5 GB ram and when using api it starts another program called ollama_llama_server.exe using around 4 GB of ram and almost 3 GB of vram. The main issue is when ollama starts it should be the olllama_server loading the model not the olllama.exe In this screenshot i was using ollama through api and i click on ollama then loads the model along side but ignoring the already running server ![Screenshot 2024-07-06 014823](https://github.com/ollama/ollama/assets/109358640/359c1c28-9cf8-4df9-a964-149658f1532f) I am not sure if it is intended behavior or not, also how do I stop ollama from loading the model at startup without turning off the service. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.48
GiteaMirror added the nvidianeeds more info labels 2026-05-03 21:27:07 -05:00
GiteaMirror commented 2026-05-03 21:27:09 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 24, 2024):

How much VRAM do you have, and which model are you loading? What does ollama ps show after you load the model?

<!-- gh-comment-id:2248595766 --> @dhiltgen commented on GitHub (Jul 24, 2024): How much VRAM do you have, and which model are you loading? What does `ollama ps` show after you load the model?
GiteaMirror commented 2026-05-03 21:27:09 -05:00
Author
Owner
Copy Link

@electro199 commented on GitHub (Aug 6, 2024):

I am using Nvidia970 4 GB VRAM with 32gb ram.

I will provide more info later today.

<!-- gh-comment-id:2270676909 --> @electro199 commented on GitHub (Aug 6, 2024): I am using Nvidia970 4 GB VRAM with 32gb ram. I will provide more info later today.
GiteaMirror commented 2026-05-03 21:27:09 -05:00
Author
Owner
Copy Link

@electro199 commented on GitHub (Aug 6, 2024):

I am not able to create the issue in v0.3.2. I will report if I encounter problem again.

<!-- gh-comment-id:2272250795 --> @electro199 commented on GitHub (Aug 6, 2024): I am not able to create the issue in v0.3.2. I will report if I encounter problem again.
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
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#65480
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?