NVIDIA Nemotron 3.5 Lightning 30B A3B BF16

Name: NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
Author: NVIDIA

by NVIDIA

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released August 2026262K context≈ 196,608 words

A mixture-of-experts model that punches above its weight by activating only 3 billion parameters per forward pass despite having 30 billion total parameters. This selective activation makes it computationally lean while retaining a broad knowledge base. Its 262K token context window is notably large, letting it handle lengthy documents without truncation.

NVIDIA Nemotron 3.5 Lightning 30B A3B BF16

by NVIDIA

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released August 2026262K context≈ 196,608 words

A mixture-of-experts model that punches above its weight by activating only 3 billion parameters per forward pass despite having 30 billion total parameters. This selective activation makes it computationally lean while retaining a broad knowledge base. Its 262K token context window is notably large, letting it handle lengthy documents without truncation.

Glossary

Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.Knowledge BaseA structured or unstructured collection of documents and facts that a system retrieves from to answer queries.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.