d1-3B

System One Arcade

Ten demos of a 3B vision-language model. Each one asks the model a few typed questions about a camera frame, a drawing or a message, and reads the answers from one forward pass.

Run it locally

On your own machine a decision comes back in tens of milliseconds, with no network in between. You need an Apple silicon Mac or a Linux machine with an NVIDIA GPU (8 GB or more), and Python 3.12 or newer.

1 · get the code

git clone https://huggingface.co/spaces/LiquidAI/system-one-arcade
cd system-one-arcade
python3 -m venv .venv && source .venv/bin/activate

2 · install and start, on a Mac

pip install -r requirements-mac.txt
python game/server.py

2 · install and start, on an NVIDIA GPU

pip install -r requirements-nvidia.txt
python game/server.py --compile

Open the address it prints. The first start downloads the model (6.2 GB) and warms up for a minute or two.