logoalt Hacker News

DominikPeters01/21/20251 replyview on HN

Indeed, for each of the words it got it right.


Replies

bt1a01/21/2025

How excellent for a quantized 27GB model (the Q6_K_L GGUF quantization type uses 8 bits per weight in the embedding and output layers since they're sensitize to quantization)