This is a quantized (NVFP4) version of NVIDIA's Nemotron-3 Ultra 550B model with 55B active parameters. It is designed for high-quality text generation and is released under an open model license. The model is hosted on Hugging Face and optimized for NVIDIA inference hardware and software.
NVIDIA Nemotron 3 Ultra 550B A55B sits in PulseGate's Quantised & converted weights category. It focuses on delivering frontier-level language model performance in a quantized form suitable for enterprise deployment. It is built as an open-source project for enterprise developers and researchers. NVIDIA Nemotron 3 Ultra 550B A55B is open source under the Open Source license. It ships for the web and API.
Behind NVIDIA Nemotron 3 Ultra 550B A55B is NVIDIA, based in the United States, and it first shipped in 2025. Key capabilities include Text Generation, Large Context, and Quantized Inference.
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