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 #3781] How to run Ollama using AMD RX 6600 XT on Windows 11? - gfx1032, workaround works on linux only #28096

New Issue
Closed
opened 2026-04-22 05:55:02 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 05:55:02 -05:00
Owner
Copy Link

Originally created by @NAME0x0 on GitHub (Apr 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3781

What is the issue?

The responses by all the LLM's are slow as the CPU is prioritised. I wish to make use of my RX 6600 XT GPU but apparently the workaround is only on Linux. Furthermore, ROCm runtime is available for RX 6600 XT but not HIP SDK which is apparently what is needed for my GPU to run LLMs. However, the documentation for Ollama says that my GPU is supported. How do I make use of it then, since it's not utilising it at all?

OS

Windows

GPU

AMD

CPU

Intel

Ollama version

0.1.32

Originally created by @NAME0x0 on GitHub (Apr 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3781 ### What is the issue? The responses by all the LLM's are slow as the CPU is prioritised. I wish to make use of my RX 6600 XT GPU but apparently the workaround is only on Linux. Furthermore, ROCm runtime is available for RX 6600 XT but not HIP SDK which is apparently what is needed for my GPU to run LLMs. However, the documentation for Ollama says that my GPU is supported. How do I make use of it then, since it's not utilising it at all? ### OS Windows ### GPU AMD ### CPU Intel ### Ollama version 0.1.32
GiteaMirror added the bug label 2026-04-22 05:55:02 -05:00
GiteaMirror commented 2026-04-22 05:55:05 -05:00
Author
Owner
Copy Link

@likelovewant commented on GitHub (Apr 21, 2024):

make sure make your rocm support first . download somewhere in github , eg, here replace the file in hip sdk.
Then git clone ollama , edit the file in ollama\llm\generate\gen_windows.ps1 ,add your gpu number there . then follow the development guide ,step1,2 , then search gfx1102 , add your gpu where ever gfx1102 show . build again or simple follow the readme file in app folder to build an ollama install then you are make your ollama running on gpu

<!-- gh-comment-id:2068051898 --> @likelovewant commented on GitHub (Apr 21, 2024): make sure make your rocm support first . download somewhere in github , eg, [here]( https://github.com/brknsoul/ROCmLibs/ ) replace the file in hip sdk. Then git clone ollama , edit the file in ` ollama\llm\generate\gen_windows.ps1` ,add your gpu number there . then follow the development guide ,step1,2 , then search `gfx1102` , add your gpu where ever `gfx1102` show . build again or simple follow the readme file in app folder to build an ollama install then you are make your ollama running on gpu
GiteaMirror commented 2026-04-22 05:55:06 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 24, 2024):

Let's keep the conversation over on the dup issue #3107

<!-- gh-comment-id:2075410378 --> @dhiltgen commented on GitHub (Apr 24, 2024): Let's keep the conversation over on the dup issue #3107
GiteaMirror commented 2026-04-22 05:55:07 -05:00
Author
Owner
Copy Link

@Sohnny0 commented on GitHub (May 9, 2024):

make sure make your rocm support first . download somewhere in github , eg, here replace the file in hip sdk. Then git clone ollama , edit the file in ollama\llm\generate\gen_windows.ps1 ,add your gpu number there . then follow the development guide ,step1,2 , then search gfx1102 , add your gpu where ever gfx1102 show . build again or simple follow the readme file in app folder to build an ollama install then you are make your ollama running on gpu

Thank you very much for your method, I successfully added gfx1031, my 6700xt graphics card can run llama3 perfectly

<!-- gh-comment-id:2102742257 --> @Sohnny0 commented on GitHub (May 9, 2024): > make sure make your rocm support first . download somewhere in github , eg, [here](https://github.com/brknsoul/ROCmLibs/) replace the file in hip sdk. Then git clone ollama , edit the file in ` ollama\llm\generate\gen_windows.ps1` ,add your gpu number there . then follow the development guide ,step1,2 , then search `gfx1102` , add your gpu where ever `gfx1102` show . build again or simple follow the readme file in app folder to build an ollama install then you are make your ollama running on gpu Thank you very much for your method, I successfully added gfx1031, my 6700xt graphics card can run llama3 perfectly
GiteaMirror commented 2026-04-22 05:55:07 -05:00
Author
Owner
Copy Link

@usmandilmeer commented on GitHub (May 14, 2024):

@Sohnny0
Hi,
I am stuck and did not understand this guide and i have windows 10 and rx6600 GPU.
Can you plz guide me step by step process for windows? or if you can make a video plz do it it will really helpful for me and others

<!-- gh-comment-id:2111209465 --> @usmandilmeer commented on GitHub (May 14, 2024): @Sohnny0 Hi, I am stuck and did not understand this guide and i have windows 10 and rx6600 GPU. Can you plz guide me step by step process for windows? or if you can make a video plz do it it will really helpful for me and others
GiteaMirror commented 2026-04-22 05:55:07 -05:00
Author
Owner
Copy Link

@muhammedaligurdal commented on GitHub (Jul 22, 2024):

Video please @Sohnny0

<!-- gh-comment-id:2243678625 --> @muhammedaligurdal commented on GitHub (Jul 22, 2024): Video please @Sohnny0
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#28096
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?