llama-bench
Also: llama bench
A small tool that measures how fast a model reads and writes on your computer.
The fuller definition
llama-bench is llama.cpp's benchmarking tool. It measures prompt-processing speed (pp) and text-generation speed (tg) for a model on your hardware.
- Model file
Loaded
- Tests
pp and tg
- Result
Tokens per second
A simplified relationship, not a screenshot or a complete design.
A concrete example
llama-bench -m model.gguf prints a table with pp512 and tg128 results in tokens per second.
The distinction that matters
A benchmark measures speed on your machine, not answer quality on your tasks.
Related terms
llama.cpp
Software that runs AI models on your machine. Many local chat apps use it behind the scenes.
Hardware & hostingTokens per second
How many word-pieces the model reads or writes each second. Around 20 or more feels comfortable to read along with.
Reliability & securityBenchmark
A standard test used to compare models. A high score on it does not mean the model is good at your task.
Where it is taught
APIs and JSON: connect a model to a small programSource and further reading
MDN · Web technology glossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.