How fast is N tokens per second really?
Every local-LLM benchmark reports throughput: "47 tok/s on an M3," "180 tok/s on a 4090," "500 tok/s on Groq." Unless you've actually watched tokens stream at those rates, the numbers are hard to internalize. This is the rendering.
Start at the default 30 and read along. Then hit 1 (5 tok/s — Raspberry-Pi-class local model), 5 (60 tok/s — typical hosted Claude or GPT), 7 (200 tok/s — Groq territory), 9 (800 tok/s — Cerebras-class, where the bottleneck is your eyeballs).
Now switch between c and t at the same rate. The difference is striking — and intentional.
This approximates BPE-style tokenization, not any vendor-specific encoder ( tiktoken , Claude's tokenizer, etc. — those disagree in the details anyway).
Short words are often one token; longer identifiers split into chunks ( processUserInput → process + User + Input ); punctuation and operators usually count too.
Code is more token-dense than prose, so the same tok/s can feel very different depending on what's streaming. The benchmark number is honest; the perceptual effect varies a lot by content type — which is the gap this tool exists to expose.