And I did this with Qwen 3.8 27B FP8, while I gave my son colacao by voice from the kitchen.
Opensource diary Day 3
Made with Terresect, Qwen 3.8 27b on RTX 6000. Progress is sloooowwww.
Playing with qwen 3.8 27B in local only
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.
You have reached the end of the archive
All of qwen38