Skip to content
store
L

Laya MLX

Native MLX runtime for Laya typed decision models

by mizorewwwFree

Launch
#568in AI
0In stores

Description

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Ratings & Reviews

No ratings yet

Be the first to rate Laya MLX.

People also visit

C

Camelid

A Rust-native local inference backend

AI
Launch
A

Anubis Oss

Local LLM Testing & Benchmarking for Apple Silicon

AI
Launch
W

Whisper.cpp

Port of OpenAI's Whisper model in C/C++

AI
Launch
F

Faster Whisper

Faster Whisper transcription with CTranslate2

AI
Launch
A

Argmax Oss Swift

On-device Speech AI for Apple Silicon

AI
Launch
T

Turbo Fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

AI
Launch
See all Laya MLX alternatives

Laya MLX FAQ

What is Laya MLX?

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Is Laya MLX free?

Yes. Laya MLX is free to use.

Do I need to download Laya MLX?

No. Laya MLX runs in your browser at github.com, so there's nothing to install.

Who makes Laya MLX?

Laya MLX is made by mizorewww.

What are the best Laya MLX alternatives?

Popular alternatives to Laya MLX include Camelid, Anubis Oss and Whisper.cpp. See all Laya MLX alternatives

Developer Stuff

Badges