‹ BackHN Continuity

Thread

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

741 points · 330 comments · snehesht

  1. jnaina · · focus · HN ↗
    installed it with UD-IQ4_XS (~4-bit GGUF) on one 24 GB RTX 5090 + ~40 GB RAM. getting ~62 tok/s and 4-bit's holding up fine for coding and code refactoring.

    using it currently to decompile an old Philip CD-I game and have it build a tvOS app.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.