github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-09 01:59:50 -05:00
Code Issues 14.7k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13286] Intel Card not used even though vulkan is configured #8781

New Issue
Closed
opened 2026-04-12 21:32:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 21:32:49 -05:00
Owner
Copy Link

Originally created by @greg-hydrogen on GitHub (Dec 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13286

What is the issue?

Hello Everyone,

I currently have 3 cards in my system, 2X3060 and 1 Arc B580. I am currently using ollama version 13.0 . When starting ollama, all three cards are seen
Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-99a7d258-339f-8724-6604-14eb2c153879 filter_id="" library=CUDA compute=8.6 name=CUDA0 descript>
Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-20195d34-86c8-ebc8-5ba2-d7222dbd0eb1 filter_id="" library=CUDA compute=8.6 name=CUDA1 descript>
Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=86800be2-0000-0000-1100-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 descript>
~
however, when trying to run a model that will use more then 24GB, nothing spills over to the Intel card, in fact the intel card is not used at all

I am not sure if I am doing something wrong, but i would be great to get all three working

Thank you,
Greg

Relevant log output

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

13.0

Originally created by @greg-hydrogen on GitHub (Dec 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13286 ### What is the issue? Hello Everyone, I currently have 3 cards in my system, 2X3060 and 1 Arc B580. I am currently using ollama version 13.0 . When starting ollama, all three cards are seen Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-99a7d258-339f-8724-6604-14eb2c153879 filter_id="" library=CUDA compute=8.6 name=CUDA0 descript> Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-20195d34-86c8-ebc8-5ba2-d7222dbd0eb1 filter_id="" library=CUDA compute=8.6 name=CUDA1 descript> Dec 01 13:29:55 ai ollama[27792]: time=2025-12-01T13:29:55.469-05:00 level=INFO source=types.go:42 msg="inference compute" id=86800be2-0000-0000-1100-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 descript> ~ however, when trying to run a model that will use more then 24GB, nothing spills over to the Intel card, in fact the intel card is not used at all I am not sure if I am doing something wrong, but i would be great to get all three working Thank you, Greg ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 13.0
GiteaMirror added the bug label 2026-04-12 21:32:49 -05:00
GiteaMirror commented 2026-04-12 21:32:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 1, 2025):

Ollama doesn't support mixed-GPU model loading. A model can be loaded on the Nvidia cards, or on the Intel card, but not on all cards.

<!-- gh-comment-id:3598347553 --> @rick-github commented on GitHub (Dec 1, 2025): Ollama doesn't support mixed-GPU model loading. A model can be loaded on the Nvidia cards, or on the Intel card, but not on all cards.
GiteaMirror commented 2026-04-12 21:32:50 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Dec 2, 2025):

Going to close the issue was answered, but feel free to keep commenting.

<!-- gh-comment-id:3604185559 --> @pdevine commented on GitHub (Dec 2, 2025): Going to close the issue was answered, but feel free to keep commenting.
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#8781
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?