atomic.chat
@atomic_chat_hq
The simplest way to run open models on any hardware. Powered by TurboQuant. Team: @gladkos @skinbagwbones @AlexFromAtomic @danyurkin @quantizedden
가입 March 2026
68 팔로잉 중 18.9K 팬
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 ->
더 보기
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！
더 보기
