Hello,
Let me add here more information that might help.
I bought a Jetson Orin Nano 2 weeks ago and I’ve the same issue, even if I do not update the latest version of Ubuntu.
Here are the details of my current Jetson:
- Jetson Firmware 36.4.7
- SSD installed and configured to be used
- OS Version Ubuntu 22.04.5 LTS
I’ve tried to follow the tutorial for the Ollama:
When I run the command: ollama run llama3.2:3b
After the download of the model, I get the error:
Error: 500 Internal Server Error: llama runner process has terminated: cudaMalloc failed: out of memory
Just like @antreask , if I try the gemma3:1b it works.
Let me know if you need more information.
Regards, Tiago