Antirez/h3.c: MiniMax H3 inference engine for Mac computers
The Antirez/h3.c project provides a native inference engine for the MiniMax H3 model optimized for Apple Silicon hardware. It supports various features including prompt-to-video generation, frame conditioning, and memory-efficient session management.
Why it matters
This tool enables developers to run advanced generative AI models locally on Mac hardware, improving accessibility and performance for AI researchers.
Native MiniMax-H3 inference for Apple Silicon. The project is being built as a sequence of working vertical slices: deterministic host/model metadata first, then portable Metal block parity, prompt encoding, prompt-to-video/audio, and first/last-frame conditioning and then ordered references.
Prompt-to-video/audio, first/last-frame conditioning, and ordered Ref2VA image/video/audio references work end to end. The current work is incremental H3-specific Metal performance and memory optimization on M3 Max and M5 Max.
1. Build and inspect the model The examples assume that the Hugging Face snapshot is in ./MiniMax-H3 and that FFmpeg and FFprobe are available on PATH .
make -j8 mkdir -p outputs ./h3 --info -d ./MiniMax-H3 --info checks the model layout and prints the selected Metal device without mapping all weights or generating media. Run ./h3 --help for the complete CLI reference.
Without -p , the same binary starts an Iris-style interactive session:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in