Getting Started¶

Welcome to Bit-Axon, a 3.2B-parameter hybrid small language model engine built for Apple Silicon. This section walks you through everything you need to go from zero to running inference on your Mac.

What you'll need¶

• A Mac with Apple Silicon (M1 or later)
• macOS 13 (Ventura) or later
• Python 3.10 or later

The entire stack runs locally. No GPU, no cloud, no PyTorch. Just MLX, Python, and your Mac.

Pages in this section¶

Installation¶

Set up your environment and install Bit-Axon. Covers the pip package, the optional SwiftUI app for Xcode, and the development environment with linting and pre-commit hooks.

Quickstart¶

Download the model, run your first inference from the CLI, try interactive chat mode, and use the Python API directly. You'll have a working model in under five minutes.

What's next?¶

After the quickstart, check out the Guides section for deeper walkthroughs on training, quantization, inference tuning, and benchmarking. The Architecture section explains the sandwich model design, Axon-SSM layers, and memory budget in detail.