atomic.chat
@atomic_chat_hq
The simplest way to run open models on any hardware. Powered by TurboQuant. Team: @gladkos @skinbagwbones @AlexFromAtomic @danyurkin @quantizedden
加入 March 2026
68 正在關注 18.9K 粉絲
Run decision models with our llama.cpp engine ⚙️
We're bringing support for over 10 System One models into Atomic Chat, now your device makes choices 10.43x faster than Jev's API utilising only the CPU
Run decision models locally ->
顯示更多
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！
顯示更多
