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
Tuantuan
JunbiaoXue
Provides a native macOS desktop companion that uses local Laya decisions to choose behavior
jev-like-model-playground
LiuWei997
A notebook template runs lightweight System 1 models, including Laya, locally on Apple Silicon with MLX
LayaBasedAssistant
userasg
Uses Laya to route requests and gate risky actions in a local voice-and-text assistant
Laya.jl
AtelierArith
Runs Laya typed-decision models in Julia on CPU or Apple GPU
laya-mlx
Gates-456
Runs open-weight Laya typed decisions locally on Apple Silicon using MLX
laya-doom
dylanbstorey
Runs Laya in a real-time control loop to play Doom on Apple Silicon
laya-js
johnhenry
Runs Laya typed decisions in JavaScript across MLX, WebGPU and CPU backends
laya-mlx-mcp
Blackphi6
Exposes Laya-MLX typed decisions through an MCP server for Apple Silicon
codex-laya-mcp
AetherZZ2
Exposes local Laya typed-decision tools to Codex through MCP on Apple Silicon
jev-laya-explore
NachiketKandari
Evaluates the local Laya decision model alongside TypeSafe's hosted Jev
laya-mlx-benchmarks
jayluxferro
Benchmarks Laya typed-decision models running through the MLX inference port
cam-laya-mcp
vdqvinh2004
Adds optional local Laya-MLX decision tools for coding agents
laya-snake-lab
shaunthebuilder
Combines a Snake game with Laya-powered autoplay, training, and live decision probabilities
laya-r-mlx
tjameswilliams
Provides a native Rust inference engine for Laya with MLX and candle backends
laya-mlx-windows-cuda
oboroge0
Documents running the MLX Laya model on Windows with an NVIDIA GPU
jev-systemone-local
katya4oyu
Plans a local Jev-compatible System One server with MLX, Core ML, and ONNX Laya backends
SEO-Agent-using-LAYA
07anishu12
Audits websites and uses Laya MLX inference to classify and prioritize SEO issues
MacJev-322M-4K-Laya
lawrence3699
Provides a fine-tuned Laya-derived decision model for local Mac agents
Autonomous-Decision-Intelligence-Platform-ADIP-
Ayyankhan101
Blueprints a local Laya-based decision platform using the laya-mlx runtime
MacJev-322M-4K-Laya-MLX
lawrence3699
Runs the MacJev typed-decision model natively on Apple silicon with MLX and compares it with Laya
stf-sim
JonRoosevelt
Simulates Brazilian Supreme Court cases using local Laya decisions, retrieval and bias probes
identity-jev
clawdreyhepburn
Fine-tunes Laya to rank identity and authentication standards from plain-language queries
zhiyan
liuqing0224
Provides macOS chat assistance with local Laya analysis and generated reply suggestions
Verdict
TobyNoSkillSon
Keeps local System One models, including Laya, ready for coding-agent classification and scoring
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