Ollama

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

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

Download

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

Quickstart

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

ollama run llama2

Model library

ollama includes a library of open-source 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

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.

Examples

Run a model

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

Create a custom model

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.

Pull a model from the registry

ollama pull orca

Listing local models

ollama list

Model packages

Overview

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

Building

go build .

To run it start the server:

./ollama serve &

Finally, run a model!

./ollama run llama2

REST API

POST /api/generate

Generate text from a model.

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