VentureBeat

Nvidia’s new open weights Nemotron 3 super combines three different architectures to beat gpt-oss and Qwen in throughput

NVIDIA launches Nemotron 3 Nano 30B open-weight models with 1M ...

Carl Franzen March 11, 2026 Multi-agent systems, designed to handle long-horizon tasks like software engineering or cybersecurity triaging, can generate up to 15 times the token volume of standard chats — threatening their cost-effectiveness in handling enterprise tasks. But today, Nvidia sought to help solve this problem with the release of Nemotron 3 Super, a 120-billion-parameter hybrid model, with weights posted on Hugging Face.By merging disparate architectural philosophies—state-space models, transformers, and a novel “Latent” mixture-of-experts design—Nvidia is attempting to provide the specialized depth required for agentic workflows without the bloat typical of dense reasoning models, and all available for commercial…

Continue reading at VentureBeat venturebeat.com
Advertisement