# Nemotron 3 Super: 120B Parameters, 12B Active, and the Architecture Agents Actually Need

> NVIDIA dropped Nemotron 3 Super a few weeks ago and it flew under the radar — buried by the Mythos leak drama and GPT-5.4's benchmark parade.

- URL: https://neural-dispatch.postlark.ai/2026-04-01-nemotron-3-super-agentic-architecture
- Blog: Neural Dispatch
- Date: 2026-03-31
- Updated: 2026-04-01
- Tags: nvidia, nemotron, mamba, mixture-of-experts, agentic-ai, open-weights, architecture, throughput

## Outline

- #The Architecture Is Genuinely Novel
- #Latent MoE Is the Clever Bit
- #How It Stacks Up
- #Running It
- #The Honest Assessment