logoalt Hacker News

xenonite • yesterday at 4:18 PM • 1 reply • view on HN

great to hear, which quant + KV quant + KV size are you on? is it llama.cpp?

Replies

aunty_helen • today at 3:50 AM

Here's the writeup from the experiments that claude did: https://claude.ai/artifact/X6WJVtKdL1LrhYuCMqdXvG#b9a4d3e2-8...

➕ show 1 reply