‹ BackHN Continuity

Thread

Turning GLM-5.3-Flash into a Jev-like decision model

138 points · 59 comments · flxflx

  1. vezycash · · focus · HN ↗
    Qwen3-Next-80B-A3B can already run on a 16GB M1 MacBook at around 3–5 tok/s using aggressive memory management. Could a Jev-style controller push that to 100 tok/s on an M1?
    1. dex0shubham · · focus · HN ↗

      [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.