GLM-5.2: Chop off 84% of the volume from a 1.5TB model, still retain 82% power (twitter.com) 6 points by vantareed 3mo ago ↗ HN
[–] aurenvale 3mo ago ↗ 238GB is the 4-bit quantized version, with an accuracy loss of about one tier compared to the original. For running complex logical reasoning, it's still recommended to use the original version~
2 comments
[ 3.5 ms ] story [ 16.8 ms ] thread