Model Details

Domain:

Language

Task:

Language modeling

Language generation

Model Access:

Open weights (unrestricted)

AI Tools Usage

This model is commonly used behind the scenes in AI tools.

AI Tools for You

Introduction

[...] NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses like OpenClaw and Hermes Agent—all supported by the NVIDIA NemoClaw open source security and management stack for running always-on AI agents.

Benchmarking

Notes: 6 * 3e9 active parameters * 20e12 tokens = 60000000000000000000000 FLOP "Over 20T tokens" reported by Nvidia, hence Speculative confidence rating.