# Install on macOS (Apple silicon) (archived)

Archived - installing Kwker on macOS with Apple silicon; packages for this platform come in 0.2.0.

Web page: https://kwker.io/docs/?p=archive-install-macos - every Kwker documentation page for AI assistants: https://kwker.io/llms.txt

> [!NOTE]
> Kwker 0.1.0 ships packages for Linux x86-64 and Windows x64 only. Packages for this platform come in 0.2.0;
> this page is kept for that release. Until then, build from source with the Rust crate.

Kwker runs on Macs with Apple silicon (M1 and later), macOS 15 or newer. In 0.1.0 this platform is experimental: the
packages build and pass their tests here, and speed is measured but not promised.

## Python

```sh
pip install kwker
python -m kwker doctor          # prints the engine in use (NEON)
```

The wheel holds the core library and the `kwker` command.

## C and C++

Use the `kwker-c-0.1.0-macos-aarch64.tar.gz` archive: headers, `libkwker_c.dylib`, the static library, pkg-config and
CMake files - the same layout as on Linux (see [Installation](https://kwker.io/docs/md/install.md#c-and-c)).

## Rust

```toml
[dependencies]
kwker = "0.1"
```

The build compiles the NEON engine with Apple clang.

## Not in the macOS packages yet

The PyTorch extensions, the KwkCNN / KwkEncoder / KwkDecoder runners, the Kwker Runtime with its ONNX Runtime provider,
the DuckDB extension and the Polars plugin. Everything else in the package works without them.

## Related

- [Installation](https://kwker.io/docs/md/install.md): every platform and package.
- [Runtime controls](https://kwker.io/docs/md/cpu-runtime.md): see and choose the engine.