laya-mlx: Laya on Apple Silicon, 60 decisions a second

# Laya-MLX



**Open-weight typed decisions, running natively on Apple Silicon.**

**13.4 ms** median end-to-end for a short English typed decision. **7.4 ms** with the multilingual checkpoint. **0 output tokens.** Local MLX inference, with no PyTorch, Transformers runtime, or cloud API.

[中文](https://github.com/mizorewww/laya-mlx/blob/main/README.zh-CN.md) · [Benchmarks](https://github.com/mizorewww/laya-mlx/blob/main/BENCHMARKS.md) · [Snake demo](https://github.com/mizorewww/laya-mlx/blob/main/docs/SNAKE_DEMO.md) · [Hugging Face weights](https://huggingface.co/aac6fef/laya-mlx)

The GIF is an original-speed render of a real local Snake run. Every move calls Laya; the visible cycle safety layer can correct unsafe proposals. The latency figures above are the separate **one-question API benchmark**, not the frame time of the three-question Snake loop. [Watch the 30-second MP4](https://github.com/mizorewww/laya-mlx/blob/main/docs/assets/snake-demo.mp4) · [Snake speed and stability](https://github.com/mizorewww/laya-mlx/blob/main/docs/SNAKE_BENCHMARKS.md).

## Quick start

```bash
pip install laya-mlx
```

```python
import laya_mlx as laya

agent = laya.load("aac6fef/laya-mlx")
result = agent.predict(
    "I was billed twice. Please refund the duplicate.",
    {
        "department": {
            "type": "choice",
            "instructions": "Who should handle this?",
            "criteria": ["billing", "technical", "sales"],
        }
    },
)
print(result["answers"]["department"])
```

Apple Silicon, Python 3.11+, macOS 14+. First load downloads the checkpoint; later inference is fully local. The measured environment is macOS 27.2, Python 3.12.13 and MLX 0.32.2. That MLX release supplies macOS 14, 15 and 26 wheels; the local installer selected the 26 wheel. Older suppor