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 #5797] support for arm linux #65651

New Issue
Closed
opened 2026-05-03 22:03:06 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 22:03:06 -05:00
Owner
Copy Link

Originally created by @olumolu on GitHub (Jul 19, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5797

Originally assigned to: @dhiltgen on GitHub.

Support for arm linux build so it can be installed in arm laptops which will be coming with new snapdragon x elite cpus with a good npu

Originally created by @olumolu on GitHub (Jul 19, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5797 Originally assigned to: @dhiltgen on GitHub. Support for arm linux build so it can be installed in arm laptops which will be coming with new snapdragon x elite cpus with a good npu
GiteaMirror added the feature request label 2026-05-03 22:03:07 -05:00
GiteaMirror commented 2026-05-03 22:03:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 20, 2024):

#2589, #5360

<!-- gh-comment-id:2241332289 --> @rick-github commented on GitHub (Jul 20, 2024): #2589, #5360
GiteaMirror commented 2026-05-03 22:03:58 -05:00
Author
Owner
Copy Link

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

@olumolu we already build ARM64 linux binaries. e.g. https://github.com/ollama/ollama/releases/download/v0.2.7/ollama-linux-arm64

If those don't work, please share more details and I'll reopen the issue.

<!-- gh-comment-id:2243953797 --> @dhiltgen commented on GitHub (Jul 22, 2024): @olumolu we already build ARM64 linux binaries. e.g. https://github.com/ollama/ollama/releases/download/v0.2.7/ollama-linux-arm64 If those don't work, please share more details and I'll reopen the issue.
GiteaMirror commented 2026-05-03 22:04:00 -05:00
Author
Owner
Copy Link

@zuyingwo-lenovo commented on GitHub (Jul 31, 2024):

is there anybody working on enabling this on AWS EC2 ARM instance?

this is o screenshot when i tried to install this on g5g instance; not supported yet, any plan?

image

<!-- gh-comment-id:2259476053 --> @zuyingwo-lenovo commented on GitHub (Jul 31, 2024): is there anybody working on enabling this on AWS EC2 ARM instance? this is o screenshot when i tried to install this on g5g instance; not supported yet, any plan? ![image](https://github.com/user-attachments/assets/20a2cca4-1f77-4014-8d16-15a8775e0ead)
GiteaMirror commented 2026-05-03 22:04:07 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Aug 2, 2024):

@zuyingwo-lenovo it looks like there might be a slight misalignment on architecture name...

It looks like nvidia is calling it arm64 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/ but our install script uses uname -m which expands to aarch64

Until we get that fixed, you can follow the guidance on the message and install the cuda drivers manually, then Ollama should work on the GPU.

<!-- gh-comment-id:2264249038 --> @dhiltgen commented on GitHub (Aug 2, 2024): @zuyingwo-lenovo it looks like there might be a slight misalignment on architecture name... It looks like nvidia is calling it `arm64` https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/ but our install script uses `uname -m` which expands to `aarch64` Until we get that fixed, you can follow the guidance on the message and install the cuda drivers manually, then Ollama should work on the GPU.
GiteaMirror commented 2026-05-03 22:04:11 -05:00
Author
Owner
Copy Link

@daffodils-ai commented on GitHub (Jan 17, 2026):

can any body let me know how can i accelerate it on snapdragon x , i have hp omnibook 5 running with 16gb of ram and qualcomm adreno gpu 8gb, i have installed ollama on ubuntu via wsl, however my cpu is beings saturated at 90-100% and gpu is still 2% utilized

<!-- gh-comment-id:3764290878 --> @daffodils-ai commented on GitHub (Jan 17, 2026): can any body let me know how can i accelerate it on snapdragon x , i have hp omnibook 5 running with 16gb of ram and qualcomm adreno gpu 8gb, i have installed ollama on ubuntu via wsl, however my cpu is beings saturated at 90-100% and gpu is still 2% utilized
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 feature request
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#65651
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?