Nemotron 3.5 Lightning specs, prices, where it runs and its benchmark standing

Name: Nemotron 3.5 Lightning
Author: Nvidia

open weights · top 10 on 0 of 2 · released Aug 11, 2026

Provider: Nvidia
Release date: Aug 11, 2026; Boards
Parameters: 31.6B total, 3B active per token; Hugging Face
Modalities: Text to Text; OpenRouter
License: OpenMDW 1.1; Hugging Face
Context window: 262K tokens; Pricing
Pricing: $0.03 in / $0.12 out per 1M tokens; All prices
Hosting: 5 priced API routes · OpenRouter · self-host: weights on Hugging Face; Pricing
Hardware: Estimate: about 66 GB of weights as published (BF16), about 32 GB at 8-bit, about 16 GB at 4-bit, plus memory for the context; Hugging Face config
Weights: Open weights
Benchmarks: 2 boards captured

Rank	Board	Category	Score	Of	Over time
38	AA SpeedSpeed · as “Nemotron 3.5 Lightning” Unverified	Speed	4 tok/s	43
43	AA IntelligenceReasoning · as “Nemotron 3.5 Lightning”	Reasoning	5.5	50

Versions and release history

2 versions in this line since Aug 11, 2026, from Pricing, OpenRouter and the boards.

Version	Released	Source
Nemotron 3.5 Lightningthis model	Aug 11, 20263 months ago	Boards
Nemotron 3.5 Lightning 30B A3B

Category ranks, more models and catalog changes