github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9787] Make ollama can run multiple models parallel #6400

New Issue
Closed
opened 2026-04-12 17:55:32 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 17:55:32 -05:00
Owner
Copy Link

Originally created by @nhantran0506 on GitHub (Mar 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9787

I've noticed that ollama can support run parallel but the logic seem to be odd. For example if I want to run llama3.2 parallel, would it be faster to just load 2 or more llama3.2 then run it seperately ? For this problem Ollama currently load 1 model and make it run "parallel".

Originally created by @nhantran0506 on GitHub (Mar 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9787 I've noticed that ollama can support run parallel but the logic seem to be odd. For example if I want to run llama3.2 parallel, would it be faster to just load 2 or more llama3.2 then run it seperately ? For this problem Ollama currently load 1 model and make it run "parallel".
GiteaMirror added the feature request label 2026-04-12 17:55:32 -05:00
GiteaMirror commented 2026-04-12 17:55:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 16, 2025):

ollama doesn't run more than one copy of a model at once. To run concurrent requests, set OLLAMA_NUM_PARALLEL. ollama will load the model and create a separate context for parallel request.

<!-- gh-comment-id:2727360050 --> @rick-github commented on GitHub (Mar 16, 2025): ollama doesn't run more than one copy of a model at once. To run concurrent requests, set [`OLLAMA_NUM_PARALLEL`](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests). ollama will load the model and create a separate context for parallel request.
GiteaMirror commented 2026-04-12 17:55:36 -05:00
Author
Owner
Copy Link

@Feynman1999 commented on GitHub (Mar 17, 2025):

ollama doesn't run more than one copy of a model at once. To run concurrent requests, set OLLAMA_NUM_PARALLEL. ollama will load the model and create a separate context for parallel request.

when set OLLAMA_NUM_PARALLEL to 2, for example。
Will the processing speed of each request slow down? But overall, setting it to 2 will increase the efficiency of the system. Am i right?

<!-- gh-comment-id:2729260128 --> @Feynman1999 commented on GitHub (Mar 17, 2025): > ollama doesn't run more than one copy of a model at once. To run concurrent requests, set [`OLLAMA_NUM_PARALLEL`](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests). ollama will load the model and create a separate context for parallel request. when set OLLAMA_NUM_PARALLEL to 2, for example。 Will the processing speed of each request slow down? But overall, setting it to 2 will increase the efficiency of the system. Am i right?
GiteaMirror commented 2026-04-12 17:55:36 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 17, 2025):

Yes, individual requests will complete slower but the overall tokens/second of the system increases.

Image

<!-- gh-comment-id:2729598549 --> @rick-github commented on GitHub (Mar 17, 2025): Yes, individual requests will complete slower but the overall tokens/second of the system increases. ![Image](https://github.com/user-attachments/assets/1c6c3b30-93ea-46c7-95fc-681d83776267)
GiteaMirror commented 2026-04-12 17:55:38 -05:00
Author
Owner
Copy Link

@yazon commented on GitHub (Nov 4, 2025):

You can use FlexLLama to handle multiple models: https://github.com/yazon/flexllama

<!-- gh-comment-id:3484205699 --> @yazon commented on GitHub (Nov 4, 2025): You can use FlexLLama to handle multiple models: https://github.com/yazon/flexllama
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#6400
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?