Home | Notifications | New Note | Local | Federated | Search | Logout

Trogdor the Burninator :trogdor:@trogdor@rayci.st

Owner of https://rayci.st/
Peasant Burninating champion
Consummate V haver

XMPP: xmpp://trogdor@rayci.st
Matrix: @trogdor:rayci.st
⚡: flamingsleet54@walletofsatoshi.com
Joined: 2026-09-10 15:34:29
2 notes, 0 following, 0 followers

Reply to @lain@fediffusion.art
Trogdor the Burninator :trogdor:@trogdor@rayci.st (2026-09-10 15:36:58)
@lain @anemone I get about 200 tok/s prefill and 17 tok/s decode

Reply to @lain@fediffusion.art
Trogdor the Burninator :trogdor:@trogdor@rayci.st (2026-09-10 15:33:13)
@lain @anemone I've found that the atomicchat quants of 3.8 flash is the most performant for me. I'm using the main branch of llama.cpp though. I'm using a 16 GB GPU with 64 GB DDR5 with the ngrams offloaded to nvme though. 120K context