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 #8064] How can I specify the GPU for running the LLM? #5155

New Issue
Closed
opened 2026-04-12 16:15:52 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 16:15:52 -05:00
Owner
Copy Link

Originally created by @NilsHellwig on GitHub (Dec 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8064

What is the issue?

The num_gpu parameter doesn't seem to work as expected. How can I ensure the model runs on a specific GPU? I have two A5000 GPUs available.

I'm not using Docker, just installed ollama by using curl -fsSL https://ollama.com/install.sh | sh.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.1

Originally created by @NilsHellwig on GitHub (Dec 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8064 ### What is the issue? The `num_gpu` parameter doesn't seem to work as expected. How can I ensure the model runs on a specific GPU? I have two A5000 GPUs available. I'm not using Docker, just installed ollama by using `curl -fsSL https://ollama.com/install.sh | sh`. ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.1
GiteaMirror added the bug label 2026-04-12 16:15:52 -05:00
GiteaMirror commented 2026-04-12 16:15:53 -05:00
Author
Owner
Copy Link

@wqerrewetw commented on GitHub (Dec 12, 2024):

https://github.com/ollama/ollama/blob/main/docs/gpu.md

<!-- gh-comment-id:2537945638 --> @wqerrewetw commented on GitHub (Dec 12, 2024): https://github.com/ollama/ollama/blob/main/docs/gpu.md
GiteaMirror commented 2026-04-12 16:15:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 12, 2024):

num_gpu specifies how many model layers to offload to the GPU, not which GPU to use. As per the link provided by @wqerrewetw, you want CUDA_VISIBLE_DEVICES.

<!-- gh-comment-id:2539035488 --> @rick-github commented on GitHub (Dec 12, 2024): `num_gpu` specifies how many model layers to offload to the GPU, not which GPU to use. As per the link provided by @wqerrewetw, you want `CUDA_VISIBLE_DEVICES`.
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 bug
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#5155
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?