kvfit is a command-line utility that helps developers determine whether a Hugging Face LLM will fit on their GPU or DGX hardware. It accounts for model weights, KV cache or recurrent state, context length, tensor and data parallelism, and provides measured calibration. Useful for capacity planning and inference optimization in LLM deployment workflows.
kvfit is a Developer Tools product. It focuses on determining if a large language model will fit in available GPU or DGX memory before attempting to load it. kvfit is an open-source project aimed at developers. The project is open source (MIT). It runs on the command line.
Behind kvfit is Teilomillet, and the product first shipped in 2026. The project is developed in the open on GitHub with 4 commits in the last 90 days. Among its 4 catalogued features are GPU Memory Calculator, KV Cache Planning, and Model Fit Analysis.
Latest indexed changes and source events
Other apps tracked under the same category.
