laya-mlx plays Snake at 60 decisions per second on an M3 Max
介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！
Project: laya-mlx→The Laya project directory
Everything the world is building on Laya.
Laya turns any text into typed decisions in milliseconds, on your own machine. Here is what it does, and 952 projects people built with it.
real run · laya-mlx
Input text
“Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan.”
laya-mlx · 146 input tokens · 0 output tokens
Which team should handle this ticket?
choice✓ billing98%
technical1%
sales1%
How urgent is this?
scorenot urgent4%
soon15%
✓ blocking81%
Does the customer threaten to cancel or leave?
yes / no✓ yes84%
no16%
Decided in 30.7 ms · 3 typed answers · one forward pass
Real outputs from Laya, not a mock-up. Run it yourself →
- Projects
- 952
- New this week
- 952
- Platforms
- 18
Seen on X this month
All demos →
Local Laya beats Jev at Tetris on a MacBook Air
Local Laya moggs Jev at @grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->
Jev decision layer routes tasks and recovers from tool failures
jev + opus 5.5... i simply can't comprehend why everyone isn't building this yet. in my workflow, this cut costs and time by ~80%. i think it's one of the best ways to use it. → pick relevant project notes before loading the context → route suitable tasks to a faster worker → choose a recovery path when a tool fails → run focused checks before the full test suite opus handles the hard reasoning. jev picks from options the harness prepares and validates. i explain how to build the decision layer in the article below:
Laya plays Tetris locally with decisions in about 27 milliseconds
This is NOT Jev. Open source. Runs on your laptop. Decides in ~27 ms, about 200× faster than waiting on a hosted LLM. Here it is playing Tetris by itself 👇
laya-coreml runs 99.5% of operations on ANE at 3.7 ms per decision
Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: Models:
Project: FluidUse→A step-by-step Jev build guide with code and architecture
everything you need to start building with jev, in one article. code, architecture, diagrams... everything you need to follow the build and make it your own.
Directory
+ Submit yours
gutcheck
janmejai2002
Runs calibrated Jev- and Laya-style decisions on local NPUs or GPUs with agent tool leasing
2·GitHub repo
pi-pignon
siiick
A Pi coding-agent extension routes prompts by difficulty using local Laya or hosted Jev
2·GitHub repo
decidealot
psyb0t
Serves local Laya and Von decision models through TypeSafe-compatible HTTP and MCP APIs
2·GitHub repo
laya-candle
mannlohchab
Runs English Laya decision-model inference using the Candle framework
2·GitHub repo
laya-thalamus
lcbkmm
Middleware uses Laya for agent tool routing with confidence-based LLM fallback and evaluation
2·GitHub repo
openpave-jev
cnrai
Provides typed-decision commands for PAVE and Claude with local Laya and hosted Jev providers
2·GitHub repo
F
laya-multilingual-gguf
fr0stbit3
Provides F16 and quantized GGUF conversions of the multilingual Laya model for llama.cpp
665·HF model
K
open-jev-laya-multilingual-onnx
killkli
A browser-ready ONNX export of Laya multilingual for typed decisions
189·HF model
W
laya-neutron-gguf
wigcheng5566
A GGUF package of Laya's encoder and decision head for CPU and Neutron NPU inference
173·HF model
W
laya-ara
Wouze
Fine-tunes multilingual Laya for Arabic intent classification, inference, and ranking
153·HF model
L
laya-LiteRT
litert-community
Converts Laya decision encoders into LiteRT graphs for Android GPU inference
152·HF model
T
laya-onnx
tozp
Hosts ONNX-converted English Laya model weights in FP32, FP16, and INT8 formats
146·HF model
Z
laya-gguf
ZeroDegress
A GGUF conversion of Laya for inference with the laya-rust engine
135·HF model
I
laya-onnx-int8
inferenceprince
Provides an int8 weight-only ONNX export of Laya for ONNX Runtime
104·HF model
L
Laya-English-LiteRT
litert-community
Runs Laya English and typed-decision checkpoints on Android GPUs with LiteRT
94·HF model
S
Laya-Multilingual-MXFP8
sahilchachra
An MXFP8 MLX quantization of Laya multilingual's encoder backbone for Apple Silicon
93·HF model
F
laya-gguf-persian-multilingual-decision
fibonacciai
A Persian-optimized multilingual GGUF conversion of the Laya typed-decision model
91·HF model
D
laya-en-fp32-swev
danielamitay
Exports Laya as a Core ML model for local typed decisions through the Swev Swift package
5·HF model
S
laya-multilingual-coreai
smdesai
Provides a Core AI conversion of multilingual Laya for typed decisions on Apple devices
1·HF model
S
laya-multilingual-onnx
soyelmismo
Provides CPU-optimized, quantized ONNX checkpoints for multilingual Laya
1·HF model
A
laya-typed-decisions-web-q8
alfred361
Provides a quantized web build of Laya typed-decision models
1·HF model
V
layaForWeb
VishalMysore
Provides quantized ONNX checkpoints and a demo for running Laya in browsers
1·HF model
R
laya-onnx
rarha
Provides an ONNX export of the Laya model
1·HF model
C
laya-banking77-v1
Cahol
Fine-tunes Laya for classifying customer messages into the 77 BANKING77 banking intents
1·HF model