Installation
Install mach from PyPI, add optional speculative decoding, and verify the setup.
Install from PyPI
Requires an Apple Silicon Mac, macOS, and Python 3.12+.
pip install mach-engineThis installs the engine and its console scripts:
| Command | Role |
|---|---|
mach-serve | OpenAI- and Anthropic-compatible HTTP server |
mach-generate | One-shot CLI generation |
mach-check | Preflight: is a checkpoint servable, and does it fit in memory? |
mach-models | List locally cached checkpoints |
mach-archs | Print the supported-architecture registry |
mlx is the only framework dependency; mlx-lm is not required.
Optional: speculative decoding
Speculative decoding (~163 tok/s vs ~117 tok/s single-stream) needs the optional
dflash extra and a local draft checkpoint:
pip install "mach-engine[dflash]"Pass the draft with mach-serve --draft-dir. Without the extra or a usable draft, the
server runs the exact decode path with no configuration needed. See
Serving.
Install from source
git clone https://github.com/SyzygyResearch/mach-engine
cd mach-engine
pip install -e "."Verify
mach-check SyzygyResearch/Mach-1-Additive-35Bmach-check reports, without downloading weights, whether the pack is supported,
which serving paths it can run, and whether it fits your machine's memory
(fits / tight / wont_fit), then prints the exact serve command.
Model downloads are cached under ~/.cache/mach (override with --cache-dir on any
command).