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
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya-ultrafast
ipenywis
Runs a browser automation agent using local Laya decisions through MLX
laya-mlx
aac6fef
An MLX FP16 conversion of Laya for native inference on Apple silicon
laya-vs-jev
virajbhartiya
A side-by-side T-Rex game compares local Laya and hosted Jev decision models
sys1
alvarobartt
Serves Laya decision models through a Rust System One API with CPU, CUDA, and Metal support
arbiter
0xBakeer
Serves Laya and other typed-decision models locally with a Jev-compatible API
eikos
caiovicentino
Builds calibrated typed-decision models for finance and trading and evaluates them against Laya
laya-multilingual-mlx
aac6fef
Converts the multilingual Laya decision model to MLX for Apple silicon
MacJev-322M-4K-Laya
chaoliangUNSW
Fine-tunes Laya for long-context local Mac agents and compares it with the base model
laya-jev-lab
yibie
Compares Jev and Laya decision models and evaluates a local-first inference cascade
LayaStudio
biplovgautam
Fine-tunes Laya decision models locally on Mac and evaluates results before deployment
opendecider
manjunathshiva
Provides calibrated System 1 decision models and benchmarks them against Laya and other models
fast-jev-compaction-laya
kaiyes
Compacts OpenCode context using decisions from a locally served Laya model
laya-apple
tc3oliver
Runs Laya locally on Apple Silicon with MLX GPU and Apple Neural Engine support
laya-as-judge
rbrus
Uses Laya-MLX to evaluate models and agents with typed-decision judgments
kime
tamnd
A Rust inference engine and HTTP server runs Laya checkpoints across CPU, CUDA, and Apple GPUs
laya-typed-decisions-mlx
aac6fef
Runs Laya typed-decision inference natively on Apple silicon with MLX
MacJev-322M-4K-Laya-MLX
chaoliangUNSW
Runs the MacJev decision model natively on Apple silicon with an MLX runtime
laya-fast
DJLougen
Runs Laya typed decisions on Apple Silicon with MLX and optional Core ML execution
jev-tests
schacon
Compares Laya, Jev, Kev, and Claude in three macOS typed-decision demos
deqio
ILuce
Serves multiple typed-decision models, including Laya, through a local API and browser UI
jev-laya-benchmark
harrymunro
Benchmarks local MLX Laya against TypeSafe's hosted Jev on synthetic decision tasks
laya-mlx-voice-browser
aryanbhujade
Uses a local Laya-MLX model to turn spoken commands into browser actions on Mac
fast-browser
hamza-sahin
Automates Brave browser workflows through MCP using Jev or optional local Laya inference
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