‹ BackHN Continuity

Thread

Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone

169 points · 52 comments · edwardbzhang

  1. walrus01 · · focus · HN ↗
    I wish that "small" LLMs would stop being confidently very incorrect. Admittedly this is a bit of an intentionally esoteric test, but the confident way in which it presents a totally incorrect answer is a bit concerning.

    "please write 250 words on the etymology and history of the word schlong"

    <a href="https:&#x2F;&#x2F;pastes.io&#x2F;uhshFgn4" rel="nofollow">https:&#x2F;&#x2F;pastes.io&#x2F;uhshFgn4

    The actual origin of the word is from middle high German and Yiddish-speaking Ashkenazi Jewish communities.

    For comparison qwen 3.6 35B A3B does perfect on this and will give a solid description of the word&#x27;s real origins and how it has made it into casual profanity&#x2F;vulgarity as used in US English, and even mentions specific stand-up comedians and famous public figures of specific ethnic&#x2F;religious origin in the US NE who introduced it into wider use.

    Ask it for something that&#x27;s not a narrow niche scientific or technical field, but something that would be less common to make it into a 20B size model, and see just how it does.

    chat test link: <a href="https:&#x2F;&#x2F;chat.deepgrove.ai&#x2F;">https:&#x2F;&#x2F;chat.deepgrove.ai&#x2F;

    1. brainless · · focus · HN ↗
      Would it not be better to ask models to search the topic on the Internet and then answer? I do not understand why we expect small LLMs to answer from own knowledge.
      1. HelloUsername · · focus · HN ↗
        &gt; Ask models to search on the Internet and answer?

        To me, the benefit of running small models is that they fit on your device exactly that you don&#x27;t need any internet connection. It&#x27;s all local and offline, so you can still consult for information in any scenario.

        1. unglaublich · · focus · HN ↗
          True but they could query a local 50GB Wikipedia dump for factual info’s via embedding search. All still local.
          1. em500 · · focus · HN ↗
            I wonder if someone already made a somewhat turnkey setup like this? Small models should ideally not waste a lot of parameters on trying to memorize too much knowledge and then hallucinate &#x2F; interpolate a lot of the gaps.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.