Oh, it’s probably higher than four words per second, then. I assumed tokens was characters and used the standard “there are five characters in a word” rule of thumb.
It's about 4 charcters per token. So just over 1 token per word. I just round to 1 token per word since text most people generate does not use larger words and because larger common words are still encoded as one token (e.g. HackerNews is probably one token despite being 10 characters).
How can there be 5 tokens per word, when they have more than half the vocabulary as GPT-2/3 which has 1.3 tokens per word?
I would have guessed more like 1.5 tokens per word.