llm-cal is an open-source command-line tool that helps AI engineers and infrastructure planners calculate hardware requirements for LLM inference. It supports architecture and engine version awareness, providing honest and detailed compatibility assessments.
llm-cal sits in PulseGate's LLM eval & observability category. It focuses on determining hardware requirements and compatibility for running LLM inference workloads. It is built as an open-source project for AI engineers and infrastructure planners. The project is open source (Apache-2.0). It runs on the command line.
Behind llm-cal is FlyTOmeLight, and it first shipped in 2026. The project is developed in the open on GitHub with 47 commits in the last 90 days. Among its 5 catalogued features are hardware calculator, LLM inference analysis, and architecture-aware.
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