github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2913] Running with Ollama desktop vs ollama serve #1786

New Issue
Closed
opened 2026-04-12 11:48:46 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 11:48:46 -05:00
Owner
Copy Link

Originally created by @sofiafernandescd on GitHub (Mar 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2913

Hello, great work with this project!
I'm using Ollama models to feed my crewAI agents, but I noticed that:

  • when I turn on Ollama desktop, everything runs well
  • if I shut down Ollama desktop, and use "ollama serve" to start Ollama, my program outputs an error because it seems to be expecting a JSON request

How do I solve this? Because I wanted to run ollama in a GPU instance, and it's not so easy to get Ollama desktop running from there, so I was looking for an easy way to get the same behaviour.

Thank you so much!

Originally created by @sofiafernandescd on GitHub (Mar 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2913 Hello, great work with this project! I'm using Ollama models to feed my crewAI agents, but I noticed that: - when I turn on Ollama desktop, everything runs well - if I shut down Ollama desktop, and use "ollama serve" to start Ollama, my program outputs an error because it seems to be expecting a JSON request How do I solve this? Because I wanted to run ollama in a GPU instance, and it's not so easy to get Ollama desktop running from there, so I was looking for an easy way to get the same behaviour. Thank you so much!
GiteaMirror commented 2026-04-12 11:48:49 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Mar 4, 2024):

What OS are you using?

<!-- gh-comment-id:1977070265 --> @easp commented on GitHub (Mar 4, 2024): What OS are you using?
GiteaMirror commented 2026-04-12 11:48:50 -05:00
Author
Owner
Copy Link

@sofiafernandescd commented on GitHub (Mar 4, 2024):

@easp I'm on MacOS, and I also tried to serve ollama on a Koyeb instance. I just tested again and it seems to be working by now, in both. I don't know what caused this, but since it's solved, I'm closing the issue. Thank you

<!-- gh-comment-id:1977082798 --> @sofiafernandescd commented on GitHub (Mar 4, 2024): @easp I'm on MacOS, and I also tried to serve ollama on a Koyeb instance. I just tested again and it seems to be working by now, in both. I don't know what caused this, but since it's solved, I'm closing the issue. Thank you
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#1786
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?