logoalt Hacker News

simonwtoday at 4:33 AM1 replyview on HN

100% true - I only had five minutes so I had to edit it down to just a couple, but all of those models are excellent and keep leap-frogging each other.


Replies

rahimnathwanitoday at 5:10 AM

Looking forward to next time, hoping you mention speculative decoding and MTP :)

It would support your point about the performance of 20GB local models.