‹ BackHN Continuity

Thread

Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint

589 points · 200 comments · JonSchneider

  1. thway15269037 · · focus · HN ↗
    I wonder if they could apply the same to Qwen3.8-Flash-Next.

    If they did 60gb -> 6gb to Qwen-27B, could they possibly do the same to the MoE model. 36gb lossless 126B model seems like an impossible task.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.