LM/Performance

From Fundamental Ramen
< LM
Jump to navigation Jump to search

Quick Test: llama-benchy

Use

llama-benchy --base-url https://models.nothanks.com/v1 --pp 512 --tg 128 --model my_model --api-key sk-12345678

Install

pipx install llama-benchy

Full Test: betterbench

Use

betterbench run --endpoint https://models.nothanks.com/v1 --model my_model --api-key sk-12345678

Install

git clone https://github.com/GGZ14/BetterBench.git
uv sync
.venv/bin/activate