The title, pretty much.

I’m wondering whether a 70b model quantized to 4bit would perform better than a 7b/13b/34b model at fp16. Would be great to get some insights from the community.

  • Secret_Joke_2262@alien.topB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    A friend told me that for 70b when using q4, performance drops by 10%. The larger the model, the less it suffers from weight quantization