‹ BackHN Continuity

Thread

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

589 points · 200 comments · JonSchneider

  1. abraxas · · focus · HN ↗
    I'm not following the local mdoel scene too closely but this seems quite amazing. Is this able to be run on Apple silicon too?
    1. kamranjon · · focus · HN ↗
      "Ternary Bonsai 2 27B reaches up to 143 tokens/second on NVIDIA GeForce RTX 5090 and 46.8 tokens/second on M5 Max. On an RTX 4090, Ternary Bonsai 2 27B consumes just 0.714 mWh/token, making it 40% more energy-efficient than an 8B model running in full-precision."
      1. azatom · · focus · HN ↗
        it is like "my fridge is 2mkm (millikilometer) from my desk" m=0.001 h=3600 it should be just Ws or just J
        1. _kulang · · focus · HN ↗
          What’s wrong with milliwatt hours?
          1. azatom · · focus · HN ↗
            <a href="https:&#x2F;&#x2F;xkcd.com&#x2F;2946&#x2F;" rel="nofollow">https:&#x2F;&#x2F;xkcd.com&#x2F;2946&#x2F;

            <a href="https:&#x2F;&#x2F;xkcd.com&#x2F;3038&#x2F;" rel="nofollow">https:&#x2F;&#x2F;xkcd.com&#x2F;3038&#x2F;

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.