Nvidia releases open-weight Nemotron 3.5 Lightning model
Nvidia released Nemotron 3.5 Lightning, an open-weights model with 3.6 billion active parameters. It matches OpenAI's gpt-oss-120b on the Intelligence Index and runs at nearly 670 tokens per second.
First seen 11 Aug, 12:52 UTC on OpenRouter5 sourcesLast update 69d ago
NVIDIALaunch · 11 Aug
Nemotron 3.5 Lightning
Open-weight model
$0.08 / $0.20per M tokens, in / out
256Kcontext
Openweights
What the sources say
Linked, never rewritten. Official means the lab itself.
Official0
No word from NVIDIA yet.
Press3
OpenRouter· 11 Aug, 12:52NVIDIA: Nemotron 3.5 Lightning listed on OpenRouterSiliconANGLE· 11 Aug, 13:00Nvidia releases Nemotron 3.5 Lightning and NeMo Switchyard to give enterprise AI capability optionsThe Decoder· 11 Aug, 15:07Nvidia's open-weight Nemotron 3.5 Lightning prioritizes speed over maximum intelligenceHow it unfolded
Every source in the order it appeared. Times in UTC.
11 Aug 12:52OpenRouter NVIDIA: Nemotron 3.5 Lightning listed on OpenRouter11 Aug 13:00SiliconANGLE Nvidia releases Nemotron 3.5 Lightning and NeMo Switchyard to give enterprise AI capability options11 Aug 13:26Hacker News Nvidia Nemotron 3.5 Lightning11 Aug 15:07The Decoder Nvidia's open-weight Nemotron 3.5 Lightning prioritizes speed over maximum intelligence11 Aug 19:35Hacker News Nvidia Nemotron 3.5 Lightning and NeMo Switchyard
Keep up with NVIDIA
NVIDIA on the ScoreIts timelineFollow to mark NVIDIA's stories across the site. No account needed.