NVIDIA Nemotron-3 Super is a 120B parameter language model with an A12B active parameter count. The FP8 version provides efficient inference while maintaining model quality. It uses a mixture-of-experts architecture and is designed for high-performance text generation tasks. The model is available on Hugging Face for developers and researchers.
In the Quantised & converted weights space, NVIDIA Nemotron 3 Super 120B A12B takes a focused approach. It focuses on delivering high-performance language model capabilities with efficient inference through quantization and mixture-of-experts architecture. NVIDIA Nemotron 3 Super 120B A12B is an open-source project aimed at developers. The project is open source (Apache-2.0). NVIDIA Nemotron 3 Super 120B A12B is available on the command line and API.
It is developed by NVIDIA, and it first shipped in 2026. Development happens publicly on GitHub with 314 stars and 72 commits in the last 90 days. PulseGate's similarity index places it among 5 comparable projects. Key capabilities include Text Generation, mixture of Experts, and FP8 Quantization. It exposes integrations via a public API.
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