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.
More from coding & agent
- KDE Drafts AI Policy: Use LLMs, But Don't Tell Anyone — carsonfarmer · 2026-09-21
- 9 practical Jev API recipes: browser agent flies through Google Flights in 7 seconds — alexcovo_eth · 2026-09-21
- GitHub's 17.4k-Star stop-slop Teaches LLMs to Strip AI Writing Tells — tom_doerr · 2026-09-21
- Solo attorney running agent fleet: evidence gates to stop coding-agent regression loops — Specialist_Call_1257 · 2026-09-21
- Code review classification saves 122k tokens, author says even 10% savings is a free win — draginol · 2026-09-21
- Microsoft open-sources IQ Solution Accelerator unifying enterprise data, knowledge and decisions — adnan_hashmi · 2026-09-21