Nemotron 3.5 Lightning

Nemotron 3.5 Lightning

NVIDIA🇺🇸nvidia/nemotron-3.5-lightning
Compare

Nemotron 3.5 Lightning is NVIDIA's open 30B mixture-of-experts model with 3B active parameters and a 1M-token context window, built for fast, accurate execution within long-running agent pipelines. It is designed as a low-latency, low-cost execution layer for always-on agentic systems.

Released
Aug 11, 2026
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs

Performance

Median latency and throughput measured across recent requests.

Intelligence5.5Rank #144
Throughput283 tok/s
Latency0.75s

Latest news about Nemotron 3.5 Lightning

Recent articles and community posts, linked to their original sources.