madewithlaya

Catalog / Tools & apps

0009X posts

A home-made Snake benchmark: Jev vs Laya-MLX vs Kev-4B

Tobias built his own Snake benchmark and ran the Jev API against Laya-MLX and Kev-4B on a low-RAM MacBook. Honest take: Jev wins on quality, locals win on speed.

Open source ↗ x.comcost-time-

Also filed under Tools & apps

  1. 0005

    laya-mlx plays Snake at 60 decisions per second★

    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！ https://t.co/31KGUiNunb

    @mizorewww · Tools & apps · free, local · 60 decisions/s

  2. 0013

    Laya exported to ONNX

    ONNX export of the Laya checkpoint so it runs anywhere onnxruntime does, including browsers and edge boxes. An fp16 variant followed a day later.

    Mattepiu · Tools & apps

  3. 0010

    Laya-mlx tied with a custom JAX build on a local game benchmark

    The problem isn't the models, it's how you define the problem space, design the movements / decisions and optimize for it (batching e.g.) Jev wins for a network-based model any day. Local models tied - Laya-mlx and my custom build Jax. Look at them go.

    @tomhacks · Tools & apps

  4. 0008

    Laya beats Jev 43 to 1 with the wifi off

    Laya beat Jev 43 to 1 with the wifi turned off 86.4 decisions per second against 3.2. 1,281 moves against 47 left side is Laya, an open weights decision model, 421 million parameters, running locally off a 1GB footprint. right side is Jev 1.13.0 over an API. both got the

    @0xchewa · Tools & apps · free, local · 86.4 decisions/s vs 3.2