llm-speed is an open-source CLI tool that benchmarks the inference speed of large language models (LLMs) across various hardware setups and hosted APIs. It provides reproducible, community-verified results for AI researchers and developers seeking to optimize model performance.
In the LLM eval & observability space, llm-speed takes a focused approach. It focuses on measuring and comparing LLM inference speed across different hardware and API backends. llm-speed is an open-source project aimed at AI researchers and developers. llm-speed is open source under the Apache-2.0 license. It ships for the command line.
llm-speed first shipped in 2026. The project is developed in the open on GitHub with 4 commits in the last 90 days. Among its 5 catalogued features are LLM benchmarking, token speed measurement, and hardware detection.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do