github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7069] Support to loading multiple LLM models on the same GPU #4487

New Issue
Closed
opened 2026-04-12 15:24:46 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 15:24:46 -05:00
Owner
Copy Link

Originally created by @DenisMontes on GitHub (Oct 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7069

Hello! Is it possible to include support for loading multiple LLM models on the same GPU?

I'm trying to create an AI team that will automate tasks, but currently I can only run one inference at a time. I'm using small models around 700MB in size on a GPU with 8GB of VRAM. I know I need space for context window beyond the neural network layers. So if it's possible to run two models simultaneously in this configuration, I'll double my performance without needing to buy another GPU that would require a larger power supply and potentially a new motherboard and case."

I have some ideas on how to implement this, and I'm willing to discuss a more in-depth way to make this feature possible.

Originally created by @DenisMontes on GitHub (Oct 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7069 Hello! Is it possible to include support for loading multiple LLM models on the same GPU? I'm trying to create an AI team that will automate tasks, but currently I can only run one inference at a time. I'm using small models around 700MB in size on a GPU with 8GB of VRAM. I know I need space for context window beyond the neural network layers. So if it's possible to run two models simultaneously in this configuration, I'll double my performance without needing to buy another GPU that would require a larger power supply and potentially a new motherboard and case." I have some ideas on how to implement this, and I'm willing to discuss a more in-depth way to make this feature possible.
GiteaMirror added the feature request label 2026-04-12 15:24:46 -05:00
GiteaMirror commented 2026-04-12 15:24:48 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 1, 2024):

Ollama already does this. Use ollama ps to see which models are loaded. However, it does not support loading the same model more than once.

<!-- gh-comment-id:2387194808 --> @rick-github commented on GitHub (Oct 1, 2024): Ollama already [does this](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests). Use `ollama ps` to see which models are loaded. However, it does not support loading the same model more than once.
GiteaMirror commented 2026-04-12 15:24:49 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 1, 2024):

Hey @DenisMontes , check out this link. Given your limited VRAM you may need to set OLLAMA_NUM_PARALLEL to make this work.

<!-- gh-comment-id:2387219355 --> @pdevine commented on GitHub (Oct 1, 2024): Hey @DenisMontes , check out this [link](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-does-ollama-handle-concurrent-requests). Given your limited VRAM you may need to set `OLLAMA_NUM_PARALLEL` to make this work.
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#4487
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?