Local AI Glossary

What is Tokens per second (tok/s)?

Source: local-llm.net/glossary

The standard measure of LLM inference speed, indicating how many tokens the model generates per second. Human reading speed is approximately 4-5 words per second (~5-7 tok/s). 20+ tok/s is considered comfortable for interactive chat. 50+ tok/s exceeds reading speed.

How Tokens per second (tok/s) fits in the local AI stack

Tokens per second (tok/s) is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms