Install mozo on CPU, CUDA or Apple silicon
Mozo is one package on PyPI. It needs Python 3.10 or newer, and installs no model packages: every model's inference code is inside mozo.
pip install mozoThat installs twelve dependencies: torch, torchvision, numpy, OpenCV (headless), Pillow, PixelFlow, FastAPI, uvicorn, python-multipart, click, regex and ftfy. Check it worked:
mozo versionMozo version 1.10.0Weights arrive on first use
Installing downloads no weights. The first time you load a model, mozo downloads its weights,
checks them against the sha256 recorded in the package, and caches them in ~/.cache/mozo. The
next load reads the cache. A first load can take minutes for a multi-gigabyte model; every load
after that takes seconds.
To download ahead of time, for example while building a container image:
from mozo import weights
weights.fetch("rfdetr", "medium", device="cuda")Pass the device the model will run on: it decides which runtime a load picks, and so which files it needs.
To keep the cache somewhere else, set MOZO_CACHE. To refuse downloads entirely, set
MOZO_OFFLINE=1. Configuration has both, and how to feed an
offline machine from a mirror.
Optional runtimes
Every model runs on torch. Some families also publish ONNX or CoreML graphs, which run without torch's overhead on some devices. The extras install what those need:
pip install 'mozo[onnx]' # onnxruntime
pip install 'mozo[coreml]' # coremltools, macOS onlyNo model needs an extra. Without one, mozo simply never picks those graphs. With one installed,
runtime="auto" may pick them where they are the faster choice: CoreML for RF-DETR, YOLOv8, YOLO12
and SAM 3 on Apple silicon. Runtimes lists which family publishes
what.
NVIDIA GPUs
Mozo uses whichever torch is installed. On Linux, the default pip install torch already includes
CUDA. Where it does not, install the CUDA build of torch first, from
pytorch.org, then mozo:
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu128
pip install mozoMozo picks the best device it finds: cuda, then mps, then cpu. Ask for one yourself with
device=:
import mozo
model = mozo.get_model("rfdetr/medium", device="cpu")For ONNX on a GPU, install onnxruntime-gpu instead of the onnx extra.
Apple silicon
Torch's mps device runs on Apple silicon with no extra install. A few operations torch has not
implemented for mps yet raise an error unless they are allowed to fall back to the CPU.
mozo start allows it by itself. From Python, set it before torch is imported:
export PYTORCH_ENABLE_MPS_FALLBACK=1Install the coreml extra for the families that publish CoreML graphs. On Apple silicon those are
the fastest way to run them, and auto picks them by itself.
From source
git clone https://github.com/emrahnazif/mozo
cd mozo
pip install -e .The workflow editor's built files are committed, so you need npm only to change the editor, never to install mozo.