To get ollama up and running with NVIDIA GPU's run the following command:
docker-compose up -d
then you will exec into that container and run the install command of the model you want for example:
ollama pull llama3.2:1b
To get ollama up and running with NVIDIA GPU's run the following command:
docker-compose up -d
then you will exec into that container and run the install command of the model you want for example:
ollama pull llama3.2:1b