Run Laya on your Mac
Apple Silicon is the best-covered platform in the Laya ecosystem. Independent ports run the upstream checkpoints on the MLX GPU, through Core ML on the Neural Engine, or inside native Swift apps. Each port publishes its own speed and fidelity measurements, all taken on the author's own Mac.
308 projects
snake-laya
Cognition-Forge
Lets users play Snake against Laya using PyTorch or MLX model runtimes
homebrew-laya-mac-serve
chrisns
Provides a Homebrew tap for installing Laya Serve, a macOS app exposing an OpenAI-compatible classifier endpoint
laya-mlx-fine-tuning
canwhite
Provides MLX fine-tuning support for the Laya model
laya-mlx-wzq
smile-magic
A browser-based Gomoku game runs Laya-MLX locally to choose moves on Apple Silicon
claude-laya
jverhoeks
Scores local Claude Code session transcripts with Laya
laya-mcp
devthinker-ai
Serves Laya typed decisions over MCP and HTTP on Apple Silicon using MLX
laya-mlx
MohammadAsadi-7
Runs Laya typed-decision models natively on Apple Silicon using MLX
lunar-laya
mraad
Runs Laya typed decisions on Apple MLX to guide a lunar-landing simulation
laya-mlx-swift
MstyAI
Provides a native Swift library for running Laya inference locally with Apple MLX
dsh-laya-router
ricardochen1996
Routes agent requests using a local Laya-MLX typed-decision model
laya-mlx-demo
knishika62
Uses laya-mlx to classify Japanese virtual streamer personas and compare results with an LLM
sample-laya-mlx-http
daisuzz
Serves Laya MLX decisions through a local System One API with a Kotlin client
jev-laya-japanese-business-benchmark
snsk
Compares Jev and Laya on a Japanese business decision benchmark
slop-finder
Code-Wizard-Wilson
Detects AI-like writing styles in social feeds using a local Laya-MLX helper
Jev-agent
To3akaRin
Suggests clipboard entries based on the focused field using local Laya inference or the Jev API
verdict
NakliTechie
Serves typed decisions on macOS through Apple Foundation Models or an optional Laya backend
screenquest
DanielTea
Controls a game on Apple Silicon with screenshot perception, Laya decisions, and vision-language planning
semantic-browser
koriym
Navigates hypermedia applications by selecting server-declared links using Laya-MLX
laya-ANE
vipuldivyanshu92
Ports Laya inference to Core ML for Apple devices, with a SwiftUI iPhone demonstration app
laya-multilingual-mlx
janvavrina
Provides a multilingual Laya model in MLX format
layad
rcwsr
Keeps the Laya decision model resident and serves it over HTTP with MLX or PyTorch
laya-tictactoe
Kasa-Harendra
A terminal Tic-Tac-Toe demo runs the Laya model locally through Core ML on Apple Silicon
laya-example
lim6112j
Demonstrates typed-question routing with Laya checkpoints and startup optimizations
laya-duum
Hadlock
Uses the Laya Core ML decision model to play the Duum game from semantic state
Pick a runtime
MLX (Python). laya-mlx is the most widely used port. It needs Apple Silicon, Python 3.11+ and macOS 14+:
pip install laya-mlx
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"])
Its README reports 13.42 ms P50 for one short question with the 421M English checkpoint and 7.39 ms with the 322M multilingual one, FP16 on an M3 Max.
Core ML and the Neural Engine. laya-coreml needs macOS 15+ and Python 3.11 to 3.13 (pip install laya-coreml). Its README reports 4.98 ms P50 for one short multilingual decision on the M3 Max Neural Engine. laya-apple runs the MLX GPU and the Neural Engine together and serves a Jev-compatible API:
pip install 'laya-apple[serve,ane]'
laya-apple serve # http://127.0.0.1:8642
Swift. laya-mlx-swift embeds Laya in a macOS app with MLX (about 804 MiB download). LayaKit is a Swift package over the laya-coreml bundles, and FluidUse ships a LayaManager for Core ML.
PyTorch MPS. The official laya package also runs on the Mac GPU; laya-mps wraps it in a local server with low-memory modes.
Caveats
- All of these are independent ports, not official Convai Innovations releases. Most publish fidelity checks against upstream answers; read them.
- The Neural Engine bundle in laya-coreml has a 96-token total limit covering question, options and state. Use the 1024-token general bundle for longer input.
- Latency numbers are single-machine measurements. Your Mac, input length and question count will change them.
More ways to use Laya