← All modelsEVIDENCE-LABELLED PROFILE · REVIEWED 20 AUGUST 2026

Nemotron 3 Nano 30B-A3B

Nemotron 3 Nano 30B-A3B is a curated mixture-of-experts profile for general, reasoning, tools workloads.

Official specifications + independent configuration linked

DeviceTerra has not lab-tested this exact artifact on every hardware combination. RAM and VRAM floors are LocalLens planning estimates, not publisher guarantees.

LOCALLENS RAM FLOOR32 GB
ARTIFACT SIZE~24 GB
INPUTText
LICENCENVIDIA Open Model License

Will it run?

LocalLens uses 32 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.

Check your complete system →

What is it useful for?

GeneralReasoningToolsAgents

Suggested Ollama artifact

Confirm the tag on the official page before downloading, then run:

ollama run nemotron-3-nano:30b

Start with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.

Evidence and limits

Published context: 1M published max. The source establishes specifications; it does not guarantee that maximum context fits at the LocalLens minimum RAM floor.