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 #4894] Feature: Allow setting OLLAMA_NUM_PARALLEL per model #3090

New Issue
Open
opened 2026-04-12 13:31:46 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 13:31:46 -05:00
Owner
Copy Link

Originally created by @sammcj on GitHub (Jun 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4894

It would be great if you could set OLLAMA_NUM_PARALLEL per model.

Example use case:

  • You have one large "smart" model you only ever want one request at a time going to to avoid using all your memory.
  • You have a smaller "fast" fast model (or just one with a smaller context) that you might want to allow a number of parallel requests to.

Perhaps this could be configured with a modelfile and corresponding API parameter rather than at launch time?

Originally created by @sammcj on GitHub (Jun 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4894 It would be great if you could set OLLAMA_NUM_PARALLEL per model. Example use case: - You have one large "smart" model you only ever want one request at a time going to to avoid using all your memory. - You have a smaller "fast" fast model (or just one with a smaller context) that you might want to allow a number of parallel requests to. Perhaps this could be configured with a [modelfile](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) and corresponding [API parameter](https://github.com/ollama/ollama/blob/main/docs/api.md#parameters) rather than at launch time?
GiteaMirror added the feature request label 2026-04-12 13:31:46 -05:00
GiteaMirror commented 2026-04-12 13:31:47 -05:00
Author
Owner
Copy Link

@JordanDalton commented on GitHub (Oct 24, 2024):

+1

<!-- gh-comment-id:2436054606 --> @JordanDalton commented on GitHub (Oct 24, 2024): +1
GiteaMirror commented 2026-04-12 13:31:47 -05:00
Author
Owner
Copy Link

@forReason commented on GitHub (Mar 27, 2025):

This is important, it does not make sense to use the same parallelisation for all models.
If i have a processing model with short context length, I may want many parallel instances. But for a very large model with medium context, I may require less parallelization.

<!-- gh-comment-id:2757355686 --> @forReason commented on GitHub (Mar 27, 2025): This is important, it does not make sense to use the same parallelisation for all models. If i have a processing model with short context length, I may want many parallel instances. But for a very large model with medium context, I may require less parallelization.
GiteaMirror commented 2026-04-12 13:31:48 -05:00
Author
Owner
Copy Link

@JoshJarabek7 commented on GitHub (Jun 11, 2025):

Is this a thing yet. The embedding model can handle hundreds in parallel, but Llama 4 Scout with 10M context would probably need parallelization set to 1.

<!-- gh-comment-id:2964002084 --> @JoshJarabek7 commented on GitHub (Jun 11, 2025): Is this a thing yet. The embedding model can handle hundreds in parallel, but Llama 4 Scout with 10M context would probably need parallelization set to 1.
GiteaMirror commented 2026-04-12 13:31:49 -05:00
Author
Owner
Copy Link

@megafetis commented on GitHub (Aug 15, 2025):

+1

<!-- gh-comment-id:3190864234 --> @megafetis commented on GitHub (Aug 15, 2025): +1
GiteaMirror commented 2026-04-12 13:31:49 -05:00
Author
Owner
Copy Link

@fighter3005 commented on GitHub (Aug 22, 2025):

+1

<!-- gh-comment-id:3213352778 --> @fighter3005 commented on GitHub (Aug 22, 2025): +1
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#3090
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?