<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub" -->

---
title: Introducing Nemotron 3 Super: An Open Hybrid...
description: NVIDIA has released Nemotron 3 Super, a 120B total / 12B active-parameter open model designed for multi-agent AI applications. Key architectural innovations...
canonical: https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning | daily.dev
og:description: NVIDIA has released Nemotron 3 Super, a 120B total / 12B active-parameter open model designed for multi-agent AI applications. Key architectural innovations...
og:url: https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub
og:image: https://api.daily.dev/og/posts/BcjCQnsub.png
og:image:alt: Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning

**[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 12 min read · 0 upvotes · 0 comments

## Summary

NVIDIA has released Nemotron 3 Super, a 120B total / 12B active-parameter open model designed for multi-agent AI applications. Key architectural innovations include a hybrid Mamba-Transformer MoE backbone with linear-time sequence processing, a Latent MoE that enables 4x more expert consultations at the same compute cost, multi-token prediction (MTP) for built-in speculative decoding with up to 3x speedups, and native NVFP4 pretraining optimized for Blackwell GPUs. The model supports a 1M-token context window to combat context explosion in long agentic tasks. Training involved 25 trillion tokens of pretraining, 7 million SFT samples, and multi-environment RL across 21 configurations using NeMo Gym. Weights, datasets, training recipes, and deployment cookbooks (vLLM, SGLang, TensorRT-LLM) are fully open. The model is available on Hugging Face, NVIDIA NIM, and multiple inference providers.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/>

## Similar posts on daily.dev

- [Run Highly Efficient and Accurate Multi-Agent AI with NVIDIA Nemotron 3 Super Using vLLM](https://daily.dev/posts/run-highly-efficient-and-accurate-multi-agent-ai-with-nvidia-nemotron-3-super-using-vllm-cpvrpiesj) · vLLM · 1 upvotes · 0 comments

---

Tags: [#agentic-ai](https://daily.dev/tags/agentic-ai), [#llm](https://daily.dev/tags/llm), [#mixture-of-experts](https://daily.dev/tags/mixture-of-experts), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning)

[View this post on daily.dev](https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning","url":"https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub"},"datePublished":"2026-03-11T16:02:03.078Z","dateModified":"2026-04-02T02:17:08.459Z","description":"NVIDIA has released Nemotron 3 Super, a 120B total / 12B active-parameter open model designed for multi-agent AI applications. Key architectural innovations...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/de3b9e4d58c82ee9871d6090d9012828?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/de3b9e4d58c82ee9871d6090d9012828?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning-bcjcqnsub","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"agentic-ai,llm,mixture-of-experts,reinforcement-learning","timeRequired":"PT12M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning"}]}
```

