laya-mlx plays Snake at 60 decisions per second
The port announcement: Laya on MLX, under 1 GB RAM, choosing the snake’s next move 60 times a second on a local M3 Max.
The port announcement: Laya on MLX, under 1 GB RAM, choosing the snake’s next move 60 times a second on a local M3 Max.
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
Mattepiu
GitHub
Tools & apps
-
-
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
@tomhacks
X post
Tools & apps
-
-
Jev vs locally running Laya-MLX and Kev-4B I built my own snake benchmark. Jev @typesafeai is running via API. The other models are small alternatives running on very little RAM on my Macbook! Jev seems to deliver the best quality no doubt! After running it for a while 0
@tobiaswup · Tools & apps
@tobiaswup
X post
Tools & apps
-
-
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
@0xchewa
X post
Tools & apps
free, local
86.4 decisions/s vs 3.2
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! github.com/mizorewww/laya…