nvidia

nvidia

Nemotron-Cascade-2-30B-A3B

Open 30B MoE model with 3B activated parameters delivering strong reasoning and agentic capabilities.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

nvidia provider

nvidia

Model Tree

Base

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today