[SleekEagle]

Fantastic article - I would love to see an analysis comparing larger quantized models to smaller unquantized models. e.g. is a 14b quantized model better than a 7b unquantized model?

[lhl]

Basically, the most aggressive quants for a larger sized model is always better than the unquantized model of a smaller model: https://github.com/ggerganov/llama.cpp/pull/1684

Tim Dettmers did a bunch of research on this last year as well: https://arxiv.org/abs/2212.09720