NVIDIA Nemotron Cascade 2

Nemotron Cascade 2 30B A3B is an open-weight Mixture-of-Experts (MoE) language model built on Nemotron 3 Nano 30B A3B Base. It contains 30B total parameters with 3B active parameters, activating 6 experts per token across 128 routed experts plus 1 shared expert. The model employs a 52-layer hybrid architecture with Mamba-SSM and MoE layers, 32 attention heads, and a 2,688 hidden size. Supporting a 262K token context window, it introduces multi-domain on-policy distillation within Cascade RL to maximize reasoning, agentic performance, and benchmark recovery across complex tasks.