antirez · Inference Engine

h3.c

Salvatore Sanfilippo native MiniMax-H3 inference engine for Apple Silicon, in C with Metal acceleration. Renders 512x512 at 20 steps in about 16.69 seconds on an M5 Max, 12.60 with token reduction, and roughly 3.5 seconds in aggressive four-step mode. Produces 22-frame clips at 24fps, supports first/last-frame anchoring and ordered reference conditioning. MIT.

Open the source ↗

Similar Developer Tools releases

More from antirez

  • voxtral.c

    antirez · Inference Engine · Week 6, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.