JevMade Sign in
← Back to experiments

Benchmarks & research

Jev-Guided MiniMax H3 Attention

By Kamimoto

Sign in to save or add notes
Source screenshot of Jev-Guided MiniMax H3 Attention
SOURCE SCREENSHOTFull screenshot ↗

What it does

Let Jev select sparse-attention rates across MiniMax H3 layers to shorten video generation on an RTX 4070.

Maker-reported (not independently measured by JevMade): 49 layers over 4 steps · 6:07 to 3:34 · 41.7% reported reduction

Maker post ↗ Preview source ↗
Primitives
Not stated
Platform
RTX 4070
Added
ShareX ↗LinkedIn ↗