github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3572] Support for AMD Radeon RX 570 series #64242

New Issue
Closed
opened 2026-05-03 16:43:51 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 16:43:51 -05:00
Owner
Copy Link

Originally created by @Mr-Ples on GitHub (Apr 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3572

Originally assigned to: @dhiltgen on GitHub.

What are you trying to do?

trying to use my AMD GPU to accelerate ollama output

How should we solve this?

add Support for AMD Radeon RX 570 series

What is the impact of not solving this?

currently im not using ollama that much because of it

Anything else?

ollama is the best application ever hands down

Originally created by @Mr-Ples on GitHub (Apr 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3572 Originally assigned to: @dhiltgen on GitHub. ### What are you trying to do? trying to use my AMD GPU to accelerate ollama output ### How should we solve this? add Support for AMD Radeon RX 570 series ### What is the impact of not solving this? currently im not using ollama that much because of it ### Anything else? ollama is the best application ever hands down
GiteaMirror commented 2026-05-03 16:43:53 -05:00
Author
Owner
Copy Link

@muzig commented on GitHub (Apr 11, 2024):

please, support for AMD Radeon RX 5700

<!-- gh-comment-id:2048841995 --> @muzig commented on GitHub (Apr 11, 2024): please, support for AMD Radeon RX 5700
GiteaMirror commented 2026-05-03 16:43:55 -05:00
Author
Owner
Copy Link

@navr32 commented on GitHub (Apr 14, 2024):

If you want you can with llamacpp in vulkan mode. I have test on an RX480 8G vram. but on ollama i haven't try to compile with forcing the vulkan mode of the llamacpp build integrated to ollama.
So you just use llamacpp alone..
Or you try force vulkan mode on the ollama building yourself.

<!-- gh-comment-id:2054227105 --> @navr32 commented on GitHub (Apr 14, 2024): If you want you can with llamacpp in vulkan mode. I have test on an RX480 8G vram. but on ollama i haven't try to compile with forcing the vulkan mode of the llamacpp build integrated to ollama. So you just use llamacpp alone.. Or you try force vulkan mode on the ollama building yourself.
GiteaMirror commented 2026-05-03 16:43:58 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 16, 2024):

Dup of #2503

<!-- gh-comment-id:2058017812 --> @dhiltgen commented on GitHub (Apr 16, 2024): Dup of #2503
GiteaMirror commented 2026-05-03 16:44:01 -05:00
Author
Owner
Copy Link

@windblade89 commented on GitHub (Apr 17, 2024):

Can you guys point me in the right direction to get AMD RX 580 8GB to work with this?

<!-- gh-comment-id:2062002164 --> @windblade89 commented on GitHub (Apr 17, 2024): Can you guys point me in the right direction to get AMD RX 580 8GB to work with this?
GiteaMirror commented 2026-05-03 16:44:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 23, 2024):

Oops, I referenced the wrong issue number - this is actually a dup of #2453

<!-- gh-comment-id:2072902966 --> @dhiltgen commented on GitHub (Apr 23, 2024): Oops, I referenced the wrong issue number - this is actually a dup of #2453
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#64242
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?