Models · The Decoder ·

Nvidia's open-weight Nemotron 3.5 Lightning prioritizes speed over maximum intelligence

Nvidia's open-weight Nemotron 3.5 Lightning prioritizes speed over maximum intelligence

Nvidia’s open-weight Nemotron 3.5 Lightning uses 3.6 billion active parameters and reportedly matches OpenAI’s gpt-oss-120b on the Intelligence Index. It reached nearly 670 tokens per second in the comparison, emphasizing inference speed and efficiency.

Read the full story at The Decoder →