Ollama

Create, run, and share self-contained large language models (LLMs). Ollama bundles a model’s weights, configuration, prompts, and more into self-contained packages that run anywhere.

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

Download

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

Examples

Quickstart

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

Creating a custom model

Create a Modelfile:

FROM llama2
PROMPT """
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.

User: {{ .Prompt }}
Mario:
"""

Next, create and run the model:

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

Model library

Ollama includes a library of open-source, pre-trained models. More models are coming soon. 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.

Model	Parameters	Size	Download
Llama2	7B	3.8GB	ollama pull llama2
Llama2 13B	13B	7.3GB	ollama pull llama2:13b
Orca Mini	3B	1.9GB	ollama pull orca
Vicuna	7B	3.8GB	ollama pull vicuna
Nous-Hermes	13B	7.3GB	ollama pull nous-hermes
Wizard Vicuna Uncensored	13B	7.3GB	ollama pull wizard-vicuna

Building

go build .

To run it start the server:

./ollama serve &

Finally, run a model!

./ollama run llama2