github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8822] Possibility for Proxying Ollama to local other machine? #5720

New Issue
Closed
opened 2026-04-12 17:00:40 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 17:00:40 -05:00
Owner
Copy Link

Originally created by @Gomez12 on GitHub (Feb 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8822

I find that a lot of tools / utils will look for a local Ollama install.

But I have a desktop pc with a Nvidia GPU and a laptop without a GPU.

Would it be possible to have a sort of proxy inside of Ollama (to work with tools and utils and Ollama cli itself) where I can specify another ip-adres which when available the request gets proxied to.

That way I could just use the desktop GPU from my laptop cli Ollama calls.

I have tested and it kinda works with a simple local running nginx proxy, but then the tools who use Ollama won't detect that Ollama is running.

Ideally I would like it to just have a preference for the desktop pc, but If it can't reach it then it goes 100% local to the machine?

My first thought wouldn't be to connect to a cloud machine, just a local machine with more GPU power so I can run larger models without changing anything in the workflow, just have better responses if I am at home or not.

Originally created by @Gomez12 on GitHub (Feb 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8822 I find that a lot of tools / utils will look for a local Ollama install. But I have a desktop pc with a Nvidia GPU and a laptop without a GPU. Would it be possible to have a sort of proxy inside of Ollama (to work with tools and utils and Ollama cli itself) where I can specify another ip-adres which when available the request gets proxied to. That way I could just use the desktop GPU from my laptop cli Ollama calls. I have tested and it kinda works with a simple local running nginx proxy, but then the tools who use Ollama won't detect that Ollama is running. Ideally I would like it to just have a preference for the desktop pc, but If it can't reach it then it goes 100% local to the machine? My first thought wouldn't be to connect to a cloud machine, just a local machine with more GPU power so I can run larger models without changing anything in the workflow, just have better responses if I am at home or not.
GiteaMirror added the feature request label 2026-04-12 17:00:40 -05:00
GiteaMirror commented 2026-04-12 17:00:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 4, 2025):

Some concrete details may help. I tried imagining your setup based on the supplied info and it seems to me that a local nginx proxy running on port 11434 and having two backends, ollama on the laptop and ollama on the desktop, should satisfy your requirements. Some info on why this doesn't work would be helpful.

<!-- gh-comment-id:2634343626 --> @rick-github commented on GitHub (Feb 4, 2025): Some concrete details may help. I tried imagining your setup based on the supplied info and it seems to me that a local nginx proxy running on port 11434 and having two backends, ollama on the laptop and ollama on the desktop, should satisfy your requirements. Some info on why this doesn't work would be helpful.
GiteaMirror commented 2026-04-12 17:00:42 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Feb 5, 2025):

Based on your ask, there's no need to setup a proxy. You can use a non-default host by setting OLLAMA_HOST, e.g. OLLAMA_HOST=<desktop-ip>:11434, so long as your desktop Ollama instance is configured to serve remote addresses, e.g. OLLAMA_HOST=0.0.0.0:11434.

<!-- gh-comment-id:2637828097 --> @mxyng commented on GitHub (Feb 5, 2025): Based on your ask, there's no need to setup a proxy. You can use a non-default host by setting `OLLAMA_HOST`, e.g. `OLLAMA_HOST=<desktop-ip>:11434`, so long as your desktop Ollama instance is configured to serve remote addresses, e.g. `OLLAMA_HOST=0.0.0.0:11434`.
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 feature request
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#5720
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?