Page Comparison

...

1. Ollama will not run on a login node. Request an interactive shell session from the command line with a GPU, e.g. for a 30-minute session

   Code Block
   $ interactive -t 30 -G 1 -p htc

2. Load the ollama module (to check the different versions available run module keyword ollama).

   Code Block
   $ module load ollama/0.3.12

3. Start Ollama serve in the background

   Code Block
   $ ollama-start

4. Run the model. You can find a list of available models here.
   The first time the model is run, Ollama automatically performs an ollama pull and downloads the model. If the model is downloaded, it loads it into memory and starts the chat.

   Code Block
   $ ollama run llama3.2

5. To stop the model you can type \bye on the prompt input.

   Code Block
   >>> \bye

6. To stop the Ollama serve:

   Code Block
   ollama-stop

...