Nemotron 3.5 Lightning

Name: Nemotron 3.5 Lightning
Author: NVIDIA

A customizable open 30B MoE model with 3B active parameters, providing optimal high-volume execution for autonomous agents.

Model page

View on models.dev

View on OpenRouter

Specs

Model

Family: Nemotron
Variant: 3.5 Lightning
Parameters: 30B total, 3B active (MoE)
Weights: Open
License: OpenMDW-1.1

Limits

Context: 262,144 tokens
Max output: 262,144 tokens

Modalities

Input: Text
Output: Text

Pricing

Input: Free
Output: Free

Capabilities

Reasoning: Yes
Reasoning control: On / off
Tool calling: Yes
Attachments: No

Dates

Released: 11 Aug 2026

Articles

All articles

12 Aug 2026

Nemotron 3.5 Lightning 30B-A3B: Behavioral Analysis

Pre-note. This is a behavioral audit, not a vendor takedown.

Tom Turney@no_stp_on_snek

x.com

11 Aug 2026

NVIDIA Technical Blog

NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents

NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for the execution layer of always-on agents, designed for harnesses like OpenClaw and Hermes Agent.

Chris Alexiuk and Chintan Patel

developer.nvidia.com