Laya on MLX
laya-mlx is an independent MLX port of Laya that runs the original weights on the Apple Silicon GPU with no PyTorch or Transformers runtime. It keeps upstream prompt formatting, calibration and output schema, and it is the base for many Mac demos, agents and benchmarks.
140 projects
opencode-jev-compaction
jlegends
Two OpenCode plugins prune stale tool calls and optionally refine decisions with local Laya
@gobing-ai/ts-laya-mlx
GitHub Actions
A TypeScript package connects applications to a local Laya decision backend through MLX
laya-rs
codesoda
A planned Rust runtime for local Laya decisions with Metal acceleration and a Jev-compatible HTTP API
laya-playground
marcosnovaesq
Runs Laya locally behind a TypeSafe-compatible API and provides a web UI for testing requests
openjev
gillmoreno
Demonstrates local Laya email-triage and simulated trading-tick decisions
laya-server
phaser
A Jev-compatible HTTP server serves local Laya typed decisions on Apple silicon
local-laya
binbandit
Runs Laya-MLX locally with an HTTP API and a TypeScript client
laya-server
SUSTYuxiao
A local inference wrapper and HTTP server for Laya with native and Jev-compatible prediction endpoints
laya-mario
gavinHuang
A Mario-style platformer uses Laya-MLX typed decisions to select actions on each game tick
laya-mlx-test
VansonLeung
Experiments with Laya-powered Tetris gameplay and sentence-level grammar screening
laya-car-snake
KarimHFahmy
Uses Laya to choose safe moves in a car-and-trailer grid game
computer-use-testing
yoaugust
Tests Jev, Laya, and CUA for computer-use tasks and plans further reinforcement-learning fine-tuning
calibrated-decisions-iot-demo
javierdv7
An interactive smart-home demo compares local Laya inference with Jev using shared rules
snake-laya
Cognition-Forge
Lets users play Snake against Laya using PyTorch or MLX model runtimes
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
Install
Requirements from the laya-mlx README: Apple Silicon, Python 3.11+, macOS 14+.
pip install laya-mlx
Pre-converted FP16 checkpoints are on Hugging Face: aac6fef/laya-mlx, aac6fef/laya-multilingual-mlx and aac6fef/laya-typed-decisions-mlx. You can also load the original convaiinnovations/laya IDs.
Router and CLI
The port includes the upstream language router and presets:
from laya_mlx import Router, triage_questions
router = Router(dtype="float16", max_loaded=2)
result = router.predict({"message": "发票被重复扣款，请退款。"}, triage_questions())
print(result["routing"]) # multilingual
For the terminal demo, where Laya plays Snake:
pip install 'laya-mlx[demo]'
hf download aac6fef/laya-multilingual-mlx
laya-snake
Reported numbers
On an M3 Max, FP16, one short question: 13.42 ms P50 for the 421M English model and 7.39 ms for the 322M multilingual model. The README states that all three checkpoints matched the upstream answer on 63/63 validation questions in FP32 and FP16. That measures port fidelity, not task accuracy.
Projects built on laya-mlx
- laya-ultrafast: a port of browser-use/jev-ultrafast that makes browser decisions locally.
- laya-mcp (wsargent): an MCP server with triage, guard, moderation and email tools.
- laya-fast: adds Neural Engine execution next to the MLX GPU.
- laya-jev-lab and jev-laya-benchmark: independent Jev comparisons that use laya-mlx as the Laya side.
- laya-vs-jev: Laya and Jev playing Chrome's T-Rex game side by side.
Caveats
This is not an official Convai Innovations release. Training and fine-tuning stay in the upstream project. BF16 can be requested but is not part of the published validation.
More ways to use Laya