Ollama docker compose.
Nvidia GPU.
- 7b models generally require at least 8GB of RAM
- 13b models generally require at least 16GB of RAM
- 70b models generally require at least 64GB of RAM
docker compose up -d
docker exec -it ollama bash
ollama run llama2
- Ollama provides a REST API for running and managing models.
- Ollama supports a list of open-source models available on ollama.ai/library.