Glimmer Index
Plus $4/mo

Nemotron 3.5 Lightning 30B A3B

NVIDIA · Released Aug 11, 2026 · Open weights

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

Strongest at
Writing
Better than 2% of the past year's models · one benchmark so far
Price per 1M tokens
$0 / $0
input / output · NVIDIA
Context window
262.1K
tokens in · 262.1K out
Lab announcement ↗Open in the timeline

Capability profile

Scored against 91 models released in the past year. 50 is the average model; further out is better.

This modelMedian of the past year
5090Median of the past yearCoding: -26 · Better than 0%Writing: 20 · Better than 2%Reading & documents: -47 · Better than 0%Reasoning: -40 · Better than 0%Math: -8 · Better than 0%CodingWritingReadingReasoningMath
Coding-26Better than 0% · 1 test
Writing20Better than 2% · 1 test
Reading & documents-47Better than 0% · 1 test
Reasoning-40Better than 0% · 1 test
Math-8Better than 0% · 1 test

No results yet: Science, Visual reasoning, Computer use

Where these scores come from

Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow dot rests on a single benchmark.

NVIDIA's past year

13 release days in the past year, about one every 28 days. The next is expected around Nov 19, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOctNov

More from the lab

Related article · Aug 11, 2026NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents

Specifications

RELEASE DATEAug 11, 2026
WEIGHTSOpen weights
CONTEXT WINDOW262.1K
MAX OUTPUT262.1K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext
OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.