[abofh]

If you just want a smaller vocabulary, use French? If your goal is to communicate to an LLM, maybe saving tokens isn't the all in win, unless you like reading assert gronkHitThing(true)

[kardos]

French text is somewhere around 10-30% longer than the corresponding English text. I would guess much of what you save on smaller vocabulary is lost on the lengthened text.

[ViscountPenguin]

What would matter more is the token length, depends how well your tokenizer was trained on french I guess.