Thread

Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s

741 points · 330 comments · snehesht

imnotr0b0t · 1791154318 · focus · HN ↗
Does the "Coder" variant at 32 GB actually feel usable for real coding work?
1. nacs · 1791154757 · focus · HN ↗
  Coder is not as good and seems to have noticable loss.
  Use the normal one - I've used that for long coding sessions and it worked well on multi-hour runs.

Unofficial Hacker News client; not affiliated with Y Combinator.