Source record

Published by Hacker News · Show HN (50+ points) (T2 source). The original is at https://llmspeed.dev/.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

A web-based tool that benchmarks local LLM inference speed on a user's own hardware, letting people gauge performance before purchasing new machines for running LLMs locally.

Removes guesswork from local LLM hardware decisions by letting you measure real inference speed on your existing setup first.

Cited by

No citations on record.