github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4376] Nvidia Jetson Nano can not use GPU to run ollama #49244

New Issue
Closed
opened 2026-04-28 10:59:16 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 10:59:16 -05:00
Owner
Copy Link

Originally created by @Dominic23331 on GitHub (May 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4376

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I use Jetson Nano to run ollama, but when I check jtop, I find my GPU is not work, the ollama is running in CPU. How to solve this problem?
image

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

0.1.37

Originally created by @Dominic23331 on GitHub (May 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4376 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I use Jetson Nano to run ollama, but when I check jtop, I find my GPU is not work, the ollama is running in CPU. How to solve this problem? ![image](https://github.com/ollama/ollama/assets/53283758/a3db77bd-5094-4e2a-b1a2-344db059b5cf) ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version 0.1.37
GiteaMirror added the gpubugnvidia labels 2026-04-28 10:59:16 -05:00
GiteaMirror commented 2026-04-28 10:59:20 -05:00
Author
Owner
Copy Link

@buraksumer commented on GitHub (May 19, 2024):

The same problem applies to me too.

System;
windows 11
Nvidia RTX 4090
128gb memory
i7-12700K

<!-- gh-comment-id:2119459273 --> @buraksumer commented on GitHub (May 19, 2024): The same problem applies to me too. System; windows 11 Nvidia RTX 4090 128gb memory i7-12700K
GiteaMirror commented 2026-04-28 10:59:20 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 21, 2024):

@Dominic23331 it sounds like our pre-built binaries might not be compatible with the cuda driver/library on the host. The server log will likely show more details on why we couldn't load properly on the GPU. I believe others have reported that building from source gets Ollama linked to the right cuda library for this system and should work as a workaround until we can figure out why our prebuilt arm binaries aren't working.

@buraksumer your issue is most likely something else unrelated to the ARM Jetson platform. Please go ahead and find a new issue with your server log so we can see why it's not detecting your GPU. (please make sure to upgrade to the latest version)

<!-- gh-comment-id:2123571450 --> @dhiltgen commented on GitHub (May 21, 2024): @Dominic23331 it sounds like our pre-built binaries might not be compatible with the cuda driver/library on the host. The server log will likely show more details on why we couldn't load properly on the GPU. I believe others have reported that building from source gets Ollama linked to the right cuda library for this system and should work as a workaround until we can figure out why our prebuilt arm binaries aren't working. @buraksumer your issue is most likely something else unrelated to the ARM Jetson platform. Please go ahead and find a new issue with your server log so we can see why it's not detecting your GPU. (please make sure to upgrade to the latest version)
GiteaMirror commented 2026-04-28 10:59:21 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (May 31, 2024):

We'll track Nano support in #4140

<!-- gh-comment-id:2143033871 --> @dhiltgen commented on GitHub (May 31, 2024): We'll track Nano support in #4140
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 gpu nvidia
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#49244
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?