ELSEIF
Your brief EB
349 stories from 93 feeds 193 clusters Refreshed 13 minutes ago next pull 04:06

AI Signal 497

Antirez/h3.c: MiniMax H3 inference engine for Mac computers

Antirez released h3.c, a native Metal inference engine for the MiniMax-H3 multimodal model that runs on Apple Silicon, enabling prompt-to-video generation with interactive sessions and configurable quality-speed tradeoffs.

WHY IT MATTERS

Running a large multimodal model locally on Apple Silicon removes the dependency on cloud inference for video generation, giving developers direct control over latency, cost, and data privacy. The project demonstrates that meaningful speedups are possible through partial denoising passes and layer reduction without catastrophic quality loss.

Written by elseif from the cluster below · every claim links back to a source

The three things worth knowing

01

The engine implements MiniMax-H3 inference natively on Apple Silicon using Metal, with current optimization work targeting M3 Max and M5 Max hardware.

02

Interactive sessions keep prompt conditioning, DiT, and decoder weights resident in memory so repeated prompts avoid reloading and re-encoding.

03

A four-pass denoising configuration achieved roughly 0.55 SSIM against a 29-pass reference while completing in approximately 3.5 seconds on M5 Max versus 26.4 seconds for the full run.

THE CLUSTER

Same story, 1 feed.

ORDERED BY FIRST SEEN
Hacker News Antirez/h3.c: MiniMax H3 inference engine for Mac computers Open ↗