Comment

Comment by carloslfu

It wasn't either/or, the N-gram table is part of Qwen itself and stays on disk. I’ve now added its 1.5GB MTP draft head too, it gets 86% acceptance and about 1.24× faster decoding on my 48GB Mac.
parent carloslfu 1 month ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton