Carlo del Mundo

Carlo del Mundo is a director of engineering at NVIDIA working in the area of low-precision numerics for inference and training. Carlo leads Nemotron Quantization efforts. Carlo previously worked at Apple working on efficient ML to enable performance-critical ML workloads to run on iPhone and future devices. Carlo holds a M.S. in CS from the University of Washington, and a B.S. in Computer Engineering from Virginia Tech.
Avatar photo

Posts by Carlo del Mundo

Decorative image.
Developer Tools & Techniques Jun 26, 2026

Creating the NVIDIA Nemotron 3 Ultra NVFP4 Checkpoint with NVIDIA Model Optimizer

As context windows grow longer, moving large model weights efficiently becomes critical to performance. A common way to address this is quantization, an... 16 MIN READ