News for hackers. Stuff that matters.

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

Re:Antirez/h3.c: MiniMax H3 inference engine for Mac computers by diddid on Tuesday August 11, 2026 @12:06AM (#49253261)
This is where the DGX spark makes up a bit of the ground it loses on llm work, diffusion and cuda go together like peanut butter and jelly.
[ Parent | on HN ]
Re:Antirez/h3.c: MiniMax H3 inference engine for Mac computers by embedding-shape on Tuesday August 11, 2026 @05:39AM (#49255490)
cough DiffusionGemma cough

Seriously, very dumb model compared to what you can run locally, but holy moly is it FAST on one GPU, seriously impressive. Can't wait for those to be scaled up a bit to fit perfectly within 96GB VRAM, then they'll be competitive.

[ Parent | on HN ]