@whitewhoadie: 🚨 A LOCAL 421M MODEL JUST ATE CLOUD JEV ON SPEED Laya is an open-source System 1 decision model that runs on your machine. Same Snake game, same typed decisions, 30 seconds: Laya: 86.5 decisions/sec, P50 ~9ms, score 46 Jev: 3.2 decisions/sec, 317ms API round-trip, score 1 Ships with: • 421M params, ~1GB inference memory • Millisecond local calls, no network • Typed decisions in one forward pass • Apache-2.0 and self-hosted While the cloud waits, local decides. 👉 https://github.com/NandhaKishorM/laya Who’s running decisions offline today? Drop a 🔥#greenscreenvideo

Lt Data :

That's crazy 421M. So that's gotta use like barely any memory right?

andrew k :

if jev was local, it may be faster but they dont want people copying or reading how it works

Code :

Is it CPU hostable?

Niko :

jev has a intelligence capacity of sonney 5 laya has a intelligence capacity of a potato

Victoria Foxx :

PAI will change the world

yekyam :

Laya is fast but it is not very smart unfortunately.

somefrenchcanadian :

My name is Jeff

Unknown :

they made this last year

Waqas Ahmed :

this ai only for multiple ai workflow and categorizing things not for coding👍👍👍👍👍

Department of ADHD :

What he said?

thelegend :

keep in mind laya was made a year ago

Dominus_Christos ☨ :

I was trying to tell my robot this’ll happen soon 😂😂

Dr. Proton :

Alex :

My 12 param model is light fast. Useless, but fast.