github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9317] Unsupported JetPack version detected. GPU may not be supported #68136

New Issue
Open
opened 2026-05-04 12:37:05 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 12:37:05 -05:00
Owner
Copy Link

Originally created by @fedekrum on GitHub (Feb 24, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9317

Hi.
I boot my Jetson Nano dev Kit in console mode.
Ollama performance was horrible so I checked with jtop utility while using it

Image

Re-installing Ollama I got this

>>> Installing ollama to /usr/local
>>> Downloading Linux arm64 bundle
######################################################################## 100,0%
**WARNING: Unsupported JetPack version detected.  GPU may not be supported**
>>> Adding ollama user to video group...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
>>> NVIDIA JetPack ready.
>>> The Ollama API is now available at 127.0.0.1:11434.
>>> Install complete. Run "ollama" from the command line.

cat /etc/nv_tegra_release
# R32 (release), REVISION: 7.6, GCID: 38171779, BOARD: t210ref, EABI: aarch64, DATE: Tue Nov  5 07:46:14 UTC 2024

ollama ps
NAME                ID              SIZE      PROCESSOR          UNTIL
deepseek-r1:1.5b    a42b25d8c10a    2.1 GB    31%/69% CPU/GPU    4 minutes from now

Any idea on how to make GPU work with Ollama?
Thanks

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

0.5.11

Originally created by @fedekrum on GitHub (Feb 24, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9317 Hi. I boot my Jetson Nano dev Kit in console mode. Ollama performance was horrible so I checked with jtop utility while using it <img width="1015" alt="Image" src="https://github.com/user-attachments/assets/ac0d707a-f3cf-4b47-bdc2-f0e9a7e23a90" /> Re-installing Ollama I got this ``` >>> Installing ollama to /usr/local >>> Downloading Linux arm64 bundle ######################################################################## 100,0% **WARNING: Unsupported JetPack version detected. GPU may not be supported** >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> Enabling and starting ollama service... >>> NVIDIA JetPack ready. >>> The Ollama API is now available at 127.0.0.1:11434. >>> Install complete. Run "ollama" from the command line. ``` ``` cat /etc/nv_tegra_release # R32 (release), REVISION: 7.6, GCID: 38171779, BOARD: t210ref, EABI: aarch64, DATE: Tue Nov 5 07:46:14 UTC 2024 ollama ps NAME ID SIZE PROCESSOR UNTIL deepseek-r1:1.5b a42b25d8c10a 2.1 GB 31%/69% CPU/GPU 4 minutes from now ``` Any idea on how to make GPU work with Ollama? Thanks ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-05-04 12:37:05 -05:00
GiteaMirror commented 2026-05-04 12:37:06 -05:00
Author
Owner
Copy Link

@easis commented on GitHub (Mar 25, 2025):

+1

<!-- gh-comment-id:2751664170 --> @easis commented on GitHub (Mar 25, 2025): +1
GiteaMirror commented 2026-05-04 12:37:07 -05:00
Author
Owner
Copy Link

@driversti commented on GitHub (Apr 21, 2025):

Hey folks. I've found a workaround when running in Docker. Please take a look at my comment here.

<!-- gh-comment-id:2817887701 --> @driversti commented on GitHub (Apr 21, 2025): Hey folks. I've found a workaround when running in Docker. Please take a look at my comment [here](https://github.com/ollama/ollama/issues/9503#issuecomment-2817867166).
GiteaMirror commented 2026-05-04 12:37:08 -05:00
Author
Owner
Copy Link

@easis commented on GitHub (Apr 22, 2025):

Hey folks. I've found a workaround when running in Docker. Please take a look at my comment here.

Bear in mind that we're talking about Jetson Nano (not the Orin one) :)

<!-- gh-comment-id:2821243150 --> @easis commented on GitHub (Apr 22, 2025): > Hey folks. I've found a workaround when running in Docker. Please take a look at my comment [here](https://github.com/ollama/ollama/issues/9503#issuecomment-2817867166). Bear in mind that we're talking about Jetson Nano (not the Orin one) :)
GiteaMirror commented 2026-05-04 12:37:09 -05:00
Author
Owner
Copy Link

@ZhuoQian111 commented on GitHub (May 11, 2025):

+1

<!-- gh-comment-id:2870007767 --> @ZhuoQian111 commented on GitHub (May 11, 2025): +1
GiteaMirror commented 2026-05-04 12:37:09 -05:00
Author
Owner
Copy Link

@ZhuoQian111 commented on GitHub (May 11, 2025):

I have the same issue, my device is Jetson nano. I'm not sure if Jetson Nano supports Jetpack

<!-- gh-comment-id:2870008674 --> @ZhuoQian111 commented on GitHub (May 11, 2025): I have the same issue, my device is Jetson nano. I'm not sure if Jetson Nano supports Jetpack
GiteaMirror commented 2026-05-04 12:37:11 -05:00
Author
Owner
Copy Link

@ZhuoQian111 commented on GitHub (May 11, 2025):

Image Image
<!-- gh-comment-id:2870008876 --> @ZhuoQian111 commented on GitHub (May 11, 2025): <img width="745" alt="Image" src="https://github.com/user-attachments/assets/ee141e5e-a867-449a-823f-3c3cd044df67" /> <img width="745" alt="Image" src="https://github.com/user-attachments/assets/8bf8a8a7-be7d-4bce-ac4c-c7039cc2fdd9" />
GiteaMirror commented 2026-05-04 12:37:12 -05:00
Author
Owner
Copy Link

@ZhuoQian111 commented on GitHub (May 11, 2025):

I have checked the script

Image Image It's only supports Jetpack5 and higher. the offical of nvidia have answered that jetpack5 will not support jetson nano and there is no support plan . Image In order to solve this issue, we can only hope that Ollama's official to supports the lower version of jetpack🤣😂 @fedekrum
<!-- gh-comment-id:2870018174 --> @ZhuoQian111 commented on GitHub (May 11, 2025): I have checked the script <img width="961" alt="Image" src="https://github.com/user-attachments/assets/6f6e30de-1b9b-4698-9eaa-f340c0ad0df1" /> <img width="945" alt="Image" src="https://github.com/user-attachments/assets/c43eb04d-d6e7-4e6d-badc-f9cca763e80a" /> It's only supports Jetpack5 and higher. the offical of nvidia have answered that jetpack5 will not support jetson nano and there is no support plan . <img width="1082" alt="Image" src="https://github.com/user-attachments/assets/fc254fae-359e-4a1a-9b0d-6ba2e1e49a30" /> In order to solve this issue, we can only hope that Ollama's official to supports the lower version of jetpack🤣😂 @fedekrum
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#68136
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?