Skip to content
伊藤P · 低显存图像生成实测·· 2026-10-09AI score31

MiniMax H3 + Veda tested: a 5-second video takes about 5 minutes, but a 6-second video takes 31 minutes

5秒の動画は5分、6秒の動画は31分——MiniMax H3 + Vedaで見つけた謎の崖

AI briefing

When running MiniMax H3 + Veda Sparse Attention on an RTX 3060 Ti (8GB VRAM) to generate 1376×768 video, a 5.2-second video completed in about 5 minutes, but a 6.6-second video took 31 minutes 30 seconds, a 7.3-second video rose further to 38 minutes 34 seconds, and a 10.1-second video terminated abnormally due to a CUDA memory allocation failure.

Open original note.com