Qudata
NVIDIA logo

Launch Nemotron 3.5 Lightning 30B-A3B

Fast MoE for always-on agents
By NVIDIAnemotron-3.5-lightning:30b30B parameters32K tokens of contextOpenMDW-1.1

NVIDIA's MoE with 3B active parameters for agents that run continuously. Fast generation and tool calling with moderate memory requirements.

GPU configurations for Nemotron 3.5 Lightning 30B-A3B

Nemotron 3.5 Lightning 30B-A3B benchmarks

as published by the model vendor
Nemotron 3.5 Lightning 30B-A3B scores in public benchmarks
MMLU Pro81.9
GPQA Diamond75.4
SWE-bench Verified51.6

Other models in a private environment

FAQ

Frequently asked about renting Nemotron 3.5 Lightning 30B-A3B

Which GPU does Nemotron 3.5 Lightning 30B-A3B need?

The entry configuration is 1x RTX5090, which delivers around 48 tokens per second. For more parallel requests and headroom on speed, go with 1x H200.

How much does Nemotron 3.5 Lightning 30B-A3B cost?

An hour of Nemotron 3.5 Lightning 30B-A3B runs from $1.84 to $8.20 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.

How do I call Nemotron 3.5 Lightning 30B-A3B from my code?

Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass nemotron-3.5-lightning:30b as the model name. Code written against the OpenAI API needs no changes.

Does the data stay private?

Yes. Nemotron 3.5 Lightning 30B-A3B runs on a dedicated GPU server inside a private environment: requests and responses never reach the model vendor and are not used for training.

What context window and license does Nemotron 3.5 Lightning 30B-A3B have?

Nemotron 3.5 Lightning 30B-A3B holds 32K tokens of context per request and ships under the OpenMDW-1.1 license, so you can use it commercially on your own hosting terms.