Nvidia Nemotron 3.5 Lightning Focuses on Speed in Open-Weight Model

2026-08-12

Nvidia's Nemotron 3.5 Lightning, an open-weights model with 3.6 billion active parameters, demonstrates high efficiency by matching a larger OpenAI model on the Intelligence Index. The model achieves a speed of nearly 670 tokens per second.

Source: The Decoder

Reported by VERA Newswire.