github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3130] Is it possible to run two instances of ollama #27685

New Issue
Closed
opened 2026-04-22 05:13:14 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 05:13:14 -05:00
Owner
Copy Link

Originally created by @eliranwong on GitHub (Mar 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3130

Is it possible to run two instances of ollama at the same time with different ports

Im looking for a workaround to the following issue:

https://github.com/ollama/ollama/issues/3115#issuecomment-1995168598

Originally created by @eliranwong on GitHub (Mar 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3130 Is it possible to run two instances of ollama at the same time with different ports Im looking for a workaround to the following issue: https://github.com/ollama/ollama/issues/3115#issuecomment-1995168598
GiteaMirror added the question label 2026-04-22 05:13:14 -05:00
GiteaMirror commented 2026-04-22 05:13:15 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 15, 2024):

Hi @eliranwong running 2 instances of Ollama on different ports should be possible, with the caveat that it will be quite resource intensive. Let me know how it goes.

<!-- gh-comment-id:1999452056 --> @BruceMacD commented on GitHub (Mar 15, 2024): Hi @eliranwong running 2 instances of Ollama on different ports should be possible, with the caveat that it will be quite resource intensive. Let me know how it goes.
GiteaMirror commented 2026-04-22 05:13:16 -05:00
Author
Owner
Copy Link

@dougvt-dev commented on GitHub (Oct 3, 2024):

Hey, i hav tried and it works haha. I install 1 local and 1 from docker

<!-- gh-comment-id:2390773732 --> @dougvt-dev commented on GitHub (Oct 3, 2024): Hey, i hav tried and it works haha. I install 1 local and 1 from docker
GiteaMirror commented 2026-04-22 05:13:16 -05:00
Author
Owner
Copy Link

@Mushy-Snugglebites-badonkadonk commented on GitHub (Oct 12, 2024):

Question for you @dougvt-dev, do you have the LLMs living in a central location e.g., a NAS? This way the local install doesn’t have to download a second copy of the LLM.

This is something that I am exploring as Ollama will spread the LLM to other GPUs that are available. For example, on the server running Ollama in a Docker container, I have two GPUs. When the model(s) do not fit on the main GPU, Ollama will send a portion of that model(s) to the next GPU in line. I was thinking of installing Ollama locally on my computer to expose and share its GPU across the network to add more VRAM to the pool.

However, However, I cannot figure out why Open WebUI (OWUI) cannot connect to the API on the locally installed Ollama instance on my computer.

<!-- gh-comment-id:2408398543 --> @Mushy-Snugglebites-badonkadonk commented on GitHub (Oct 12, 2024): Question for you @dougvt-dev, do you have the LLMs living in a central location e.g., a NAS? This way the local install doesn’t have to download a second copy of the LLM. This is something that I am exploring as Ollama will spread the LLM to other GPUs that are available. For example, on the server running Ollama in a Docker container, I have two GPUs. When the model(s) do not fit on the main GPU, Ollama will send a portion of that model(s) to the next GPU in line. I was thinking of installing Ollama locally on my computer to expose and share its GPU across the network to add more VRAM to the pool. However, However, I cannot figure out why Open WebUI (OWUI) cannot connect to the API on the locally installed Ollama instance on my computer.
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#27685
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?