Thread

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

741 points · 330 comments · snehesht

paulez · 1791131257 · focus · HN ↗
Pretty impressive so far, but needs more testing.
It is more useful than Qwen3.8:27b (which is already quite good) and runs faster on my 7900 XTX / 64 GB DDR4 system.
Local LLM is getting more exciting every day!
1. coderbants · 1791144375 · focus · HN ↗
  Interested to know throughput on 7900 XTX and what setup you're using?

Unofficial Hacker News client; not affiliated with Y Combinator.