inferbench-cli is an open-source CLI tool for benchmarking local LLM inference speed and providing hardware configuration advice for omlx and llama.cpp. It helps developers and researchers optimize AI model performance on their own machines.
In the LLM eval & observability space, inferbench-cli takes a focused approach. It focuses on measuring and optimizing local LLM inference performance on user hardware. It is built as an open-source project for AI developers and researchers. inferbench-cli is open source under the Apache-2.0 license. inferbench-cli is available on the command line, and it can be self-hosted.
Behind inferbench-cli is Rudrendu Paul, and the product first shipped in 2026. Development happens publicly on GitHub with 15 commits in the last 90 days. Key capabilities include LLM benchmarking, hardware advisor, and token/sec measurement.
Latest indexed changes and source events
inferbench-cli verified by the PulseGate indexer
Other apps tracked under the same category.
