sparkfit is an open-source CLI tool that assists ML infrastructure engineers in planning memory and bandwidth requirements for deploying large language models on NVIDIA DGX Spark systems. It provides unified-memory and quantization-aware analysis for efficient resource allocation.
sparkfit sits in PulseGate's Other AI category. It helps users estimate and plan memory requirements for running large language models on NVIDIA DGX Spark hardware. It is built as an open-source project for ml infrastructure engineers. sparkfit is open source under the MIT license. It runs on the command line.
It is developed by engineering87, and it first shipped in 2026. The project is developed in the open on GitHub with 14 commits in the last 90 days. Key capabilities include memory capacity planning, LLM inference analysis, and unified memory awareness.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Other projects tracked alongside this one