FRAMEWIREIndonesiaUpdated Sep 26Live wire
0:00 / 0:00

Playing with qwen 3.8 27B in local only

BadbrainSep 261
0:00 / 0:00

My goal is to unlock commodity inference.

Not just better local ai, but better ai on cheap commodity hardware... We have made a lot of progress, a P100 GPU (~$100). Running Qwen 3.8 27b at nearly 17 tok/s without speculation. Our goal is 25+ tok/s.

Shannon 🤖☠️Sep 265
0:00 / 0:00
0:00 / 0:00

Second attempt at this edit

Made with Terresect. Qwen 3.8 27b on a Single RTX 6000

WbackdownSep 251