On a very old model, it's more like 16.000 garbage words/s
Llama 3.1 8B is pretty useful for some thing. I use it to generate SQL pretty reliably for example.
They are doing an updated model in a month or so anyway, then a frontier level one "by summer".
I do wonder if there are tasks where 16k garbage words/s are more useful than 200 good words per second. Does anyone have any ideas? Data extraction perhaps?