Note: Ollama is in early preview. Please report any issues you find.

Run, create, and share large language models (LLMs).

• Download for macOS on Apple Silicon (Intel coming soon)
• Download for Windows and Linux (coming soon)
• Build from source

To run and chat with Llama 2, the new model by Meta:

ollama run llama2

ollama includes a library of open-source models:

Note: You should have at least 8 GB of RAM to run the 3B models, 16 GB to run the 7B models, and 32 GB to run the 13B models.

ollama run llama2
>>> hi
Hello! How can I help you today?

Pull a base model:

ollama pull llama2

Create a Modelfile:

FROM llama2

# set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1

# set the system prompt
SYSTEM """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
"""

Next, create and run the model:

ollama create mario -f ./Modelfile
ollama run mario
>>> hi
Hello! It's your friend Mario.

For more examples, see the examples directory.

ollama pull orca

ollama list

Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile.

go build .

To run it start the server:

./ollama serve &

Finally, run a model!

./ollama run llama2

Generate text from a model.

curl -X POST http://localhost:11434/api/generate -d '{"model": "llama2", "prompt":"Why is the sky blue?"}'