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.
260 projects
jev-codex-workbench
qualixar
Adds Jev decisions and optional local Laya-MLX routing to a Codex plugin and MCP server
laya
xosi
Runs Laya typed-decision inference locally on Apple Silicon with MLX
laya-mlx-ddz
smile-magic
A browser-based 斗地主 game lets two local AI seats play using Laya on Apple Silicon
decide
gopaljigaur
Provides a Python client that chains Laya with hosted and other decision-model backends
jev-laya-benchmark
EnesDemir143
Benchmarks TypeSafe Jev and Laya-MLX on structured issue classification
laya-learning-demo
Daryl9441
A runnable tutorial teaches Laya decision primitives, routing, fine-tuning, and comparison with Jev
tetris_for_laya
fchange
Provides a terminal Tetris environment where a local Laya model chooses each action
laya-mlx-per-turn-classifier
M37Labs
Demonstrates per-turn customer message classification with Laya on Apple Silicon
laya-rust
zerodegress
Implements a Rust inference engine for Laya with CUDA, CPU, and MLX backends
laya-exp
changtimwu
Experiments comparing an MLX Laya port with Jev and a TypeSafe-compatible Laya client
laya-lab
Alevsk
Runs Laya locally with reproducible scenarios that explore its capabilities on Apple Silicon
Tern
AmRitJain0442
A model router uses local Laya-MLX inference to select between configurable provider tiers
lime-jev
yzxoi
Adds optional Laya reranking to a local Chinese pinyin input method on Apple Silicon
laya-decision-api
bmw8080
An HTTP service wraps local Laya with OpenAPI documentation and Java, TypeScript, and Python SDKs
laya-vs-dijkstra
antonellof
Compares Laya MLX pathfinding decisions with Dijkstra on seeded weighted mazes
code-oracle
wahyuzero
Verifies code changes with AST checks and Laya-based residual-drift evaluation
laya-browser
Benny93
Uses a local Laya model to resolve plain-English selectors in browser automation
ghosthand
ameerhmz
A local macOS voice and computer-use agent uses Laya for typed decisions
pi-laya-skill-router
ericmjl
Routes pi coding-agent requests to relevant skills using a local Laya model
laya-local-guard
Kamandlou
Classifies content for safety risks locally with Laya-MLX and detects PII and secrets
laya-system1-snake
Kamandlou
A terminal Snake game uses Laya MLX to choose moves from structured game-state features
docweave
pareshbhangale
Converts PDFs to Markdown and uses Jev or Laya alongside local models for layout routing and table auditing
laya-agent
inboxxobni
Runs Laya typed decisions locally on Apple Silicon and provides an HTTP server and agent integrations
laya-router
vuongvm812
Sets up local Laya classification and Jev Router proxies for coding clients
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