Laya ported to MLX: M3 Max runs local agent 60 decisions/sec, 50x faster

sven_ai · x · 2026-09-21

A developer ported the Laya agent to Apple's MLX framework and ran it locally on an M3 Max, playing Snake with under 1GB of memory and 60 decisions per second — about 50x faster than Jev. A striking demonstration of how far Apple Silicon plus MLX can push lightweight local agents.

Original post →

More from coding & agent

coding & agent channel →