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 #14062] 2 gpu's? #9187

New Issue
Closed
opened 2026-04-12 22:02:13 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 22:02:13 -05:00
Owner
Copy Link

Originally created by @jekv2 on GitHub (Feb 4, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14062

I have a 3060TIFE and an integrated AMD GPU in the AM5 9950x.

Am I able to utilize the granite ridge GPU as well to help utilize models?

Image
Originally created by @jekv2 on GitHub (Feb 4, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14062 I have a 3060TIFE and an integrated AMD GPU in the AM5 9950x. Am I able to utilize the granite ridge GPU as well to help utilize models? <img width="387" height="563" alt="Image" src="https://github.com/user-attachments/assets/fd720388-46e6-478d-bf51-ee0a4ad1d74a" />
GiteaMirror commented 2026-04-12 22:02:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 4, 2026):

Two GPUs of different brands can't be used for a single model, so at best you could run one model per GPU. However, if I read the screen shot correctly, the AMD has only 512MB, which is only big enough for the tiniest models, eg smollm2:135m. That's assuming that the AMD GPU is even supported - you likely would have to try the Vulkan driver.

<!-- gh-comment-id:3844874007 --> @rick-github commented on GitHub (Feb 4, 2026): Two GPUs of different brands can't be used for a single model, so at best you could run one model per GPU. However, if I read the screen shot correctly, the AMD has only 512MB, which is only big enough for the tiniest models, eg [smollm2:135m](https://ollama.com/library/smollm2:135m). That's assuming that the AMD GPU is even supported - you likely would have to try the [Vulkan](https://docs.ollama.com/gpu#vulkan-gpu-support) driver.
GiteaMirror commented 2026-04-12 22:02:15 -05:00
Author
Owner
Copy Link

@jekv2 commented on GitHub (Feb 4, 2026):

Two GPUs of different brands can't be used for a single model, so at best you could run one model per GPU. However, if I read the screen shot correctly, the AMD has only 512MB, which is only big enough for the tiniest models, eg smollm2:135m. That's assuming that the AMD GPU is even supported - you likely would have to try the Vulkan driver.

Gotcha, not worth trying.

I have a GTX-960-2GD5 lying around, with 2GB,if I slap that in the windows PC, can the RTX and GTX run together to utilize one model?
https://www.techpowerup.com/gpu-specs/msi-gtx-960.b3178

Thanks.

<!-- gh-comment-id:3844973155 --> @jekv2 commented on GitHub (Feb 4, 2026): > Two GPUs of different brands can't be used for a single model, so at best you could run one model per GPU. However, if I read the screen shot correctly, the AMD has only 512MB, which is only big enough for the tiniest models, eg [smollm2:135m](https://ollama.com/library/smollm2:135m). That's assuming that the AMD GPU is even supported - you likely would have to try the [Vulkan](https://docs.ollama.com/gpu#vulkan-gpu-support) driver. Gotcha, not worth trying. I have a GTX-960-2GD5 lying around, with 2GB,if I slap that in the windows PC, can the RTX and GTX run together to utilize one model? https://www.techpowerup.com/gpu-specs/msi-gtx-960.b3178 Thanks.
GiteaMirror commented 2026-04-12 22:02:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 4, 2026):

The GTX-960 is supported and ollama should use both Nvidia GPUs when loading a model.

<!-- gh-comment-id:3846785022 --> @rick-github commented on GitHub (Feb 4, 2026): The GTX-960 is [supported](https://github.com/ollama/ollama/blob/main/docs/gpu.mdx#nvidia:~:text=980%20GTX%20970-,GTX%20960,-GTX%20950) and ollama should use both Nvidia GPUs when loading a model.
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
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#9187
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?