Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

作者：Nvidia Aaron Blakeman, Aaron Grattafiori, Aarti Basant, Abhibha Gupta, Abhinav Khattar, Adi Renduchintala, Aditya Vavre, Akanksha Shukla, A. Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Kondratenko, A. Bukharin, Alexandre Milesi, Ali Taghibakhshi, Alisa Liu, Amelia Barton, A. Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Amy Shen, Anahita Bhiwandiwalla, Andrew Tao, Ann Guan, Anubhav Mandarwal, Arham Mehta, Ashwath Aithal, Ashwin Poojary, A. Ahamed, Asma Kuriparambil Thekkumpate, Ayush Dattagupta, Banghua Zhu, Bardiya Sadeghi, B. Simkin, Ben Lanir, Benedikt Schifferer, Besmira Nushi, Bilal Kartal, B. Rouhani, Boris Ginsburg, Brandon Norick, B. Soubasis, B. Kisačanin, Brian Yu, Bryan Catanzaro, Carlo del Mundo, Chantal Hwang, Charles Wang, Cheng-Ping Hsieh, Chenghao Zhang, Chenhan Yu, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Christopher Parisien, Collin Neale, Damon Mosk-Aoyama, Dan Su, Dane S. Corneil, Daniel Afrimi, Daniel Rohrer, Daniel Serebrenik, Daria Gitman, Daria Levy, Darko Stosic, David Mosallanezhad, Deepak Narayanan, Dhruv Nathawani, Dima Rekesh, Dina Yared, Divyanshu Kakwani, Dong Ahn, Duncan Riach, Dusan Stosic, E. Minasyan, Edward Lin, E. Long, E. Long, Elena Lantz, Ellie Evans, Elliott Ning, Eric Chung, Eric Harper, Eric W. Tramel, Erick Galinkin, Erik Pounds, Evan Briones, E. Bakhturina, Faisal Ladhak, Fay Wang, Fei Jia, Felipe Soares, Feng Chen, Ferenc Galkó, Frankie Siino, Galila Agam, Ganesh Ajjanagadde, Gantavya Bhatt, G. Prasad, George Armstrong, Gerald Shen, G. Batmaz, Grigor Nalbandyan, Haifeng Qian, Harsh Sharma, Hayley Ross, Helen Ngo, Herman Sahota, Hexin Wang, Himanshu Soni, Hiren Upadhyay, Huizi Mao, Huy C Nguyen, Huy Q Nguyen, Iain Cunningham, Ido Shahaf, Igor Gitman, I. Loshchilov, Ivan Moshkov, Izzy Putterman, Jan Kautz, Jane Scowcroft, J. Casper, Jatin Mitra, Jeffrey Glick, Jenny Chen, Jesse Oliver, Jian Zhang, Jiaqi Zeng, Jie Lou, Jimmy Zhang, Jining Huang, Joey Conway, J. Guman, John Kamalu, Johnny Greco, J. Cohen, Joseph Jennings, Joyjit Daw, J. V. Vialard, Junkeun Yi, Jupinder Parmar, Kai Xu, Kan Zhu, Kari Briski, K. Cheung, K. Luna, Keshav Santhanam, Kevin J. Shih, Kezhi Kong, Khushi Bhardwaj, Krishna C. Puvvada, Krzysztof Pawelec, Kumar Anik, Lawrence C. McAfee, Laya Sleiman, Leon Derczynski, Li Ding, Lucas Liebenwein, Luis Vega, Maanu Grover, Maarten Van Segbroeck, Maer Rodrigues de Melo, Makesh Narsimhan Sreedhar, Manoj Kilaru, Maor Ashkenazi, Marc Romeijn, Mark Cai, Markus Kliegl, Maryam Moosaei, Matvei Novikov, Mehrzad Samadi, Melissa Corpuz, Mengru Wang, Meredith Price, Michael Boone, Michael Evans, Miguel Martínez, Mike Chrzanowski, M. Shoeybi, M. Patwary, Nabin Mulepati, Natalie Hereth, Nave Assaf, N. Habibi, Neta Zmora, Netanel Haber, Nicola Sessions, Nidhi Bhatia, Nikhil Jukar, Nikki Pope, Nikolai Ludwig, Nima Tajbakhsh, Nirmal Juluru, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivier Delalleau, O. Olabiyi, Omer Ullman Argov, Ouye Xie, Parth Chadha, Pasha Shamis, Pavlo Molchanov, Pawel M. Morkisz, Peter Dykas, Peter Jin, Pinky Xu, Piotr Januszewski, P. Thombre, Prasoon Varshney, Pritam Gundecha, Qing Miao, Rabeeh Karimi Mahabadi, Ran El-Yaniv, Ran Zilberstein, Rasoul Shafipour, Rich Harang, Rick Izzo, Rima Shahbazyan, Rishabh Garg, Ritika Borkar, Ritu Gala, Riyad Islam, R. Waleffe, Rohit Watve, Roi Koren, Ruoxi Zhang, Russell J. Hewett, R. Prenger, Ryan Timbrook, Sadegh Mahdavi, Sahil Modi, Samuel Kriman, Sanjay Kariyappa, S. Satheesh, Saori Kaji, Satish Pasumarthi, Sean Narentharen, Sean Narenthiran, Seonmyeong Bak, Sergey Kashirsky, Seth Poulos, Shahar Mor, Shanmugam Ramasamy, Shantanu Acharya, Shaona Ghosh, Sharath Turuvekere Sreenivas, S. Thomas, Shiqing Fan, Shreya Gopal, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shuoyang Ding, Siddharth Singh, Simeng Sun, Smita Ithape, Somshubra Majumdar, Soumye Singhal, Stefania Alborghetti, Stephen Ge, Sugam Devare, Sumeet Kumar Barua, Suseella Panguluri, Suyog Gupta, S. Priyadarshi, Syeda Nahida Akter, Tan Bui, Teodor-Dumitru Ene, Terry Kong, Thanh Do, Tijmen Blankevoort, Tom Balough, Tomer Asida, Tomer Bar Natan, T. Konuk, Twinkle Vashishth, Udi Karpas, Ushnish De, Vahid Noorozi, V. Noroozi, V. Srinivasan, V. Elango, V. Korthikanti, V. Kurin, Vitaly Lavrukhin, Wanli Jiang, W. Ahmad, Wei Du, Wei Ping, Wenfei Zhou, Will Jennings, William Zhang, Wojciech Prazuch, Xiaowei Ren, Yashaswi Karnati, Yejin Choi, Yev Meyer, Yi-Fu Wu, Yian Zhang, Ying Lin, Yonatan Geifman, Yonggan Fu, Yoshi Subara, Yoshi Suhara, Yubo Gao, Zach Moshe, Zhen Dong, Zihan Liu, Zijia Chen, Zijie Yan · 发表于：arXiv.org · 年份：2025 · DOI：10.48550/arxiv.2512.20848 · 被引用次数：76 · 研究领域：Computer Science

We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on diverse environments. Nemotron 3 Nano achieves better accuracy than our previous generation Nemotron 2 Nano while activating less than half of the parameters per forward pass. It achieves up to 3.3x higher inference throughput than similarly-sized open models like GPT-OSS-20B and Qwen3-30B-A3B-Thinking-2507, while also being more accurate on popular benchmarks. Nemotron 3 Nano demonstrates enhanced agentic, reasoning, and chat abilities and supports context lengths up to 1M tokens. We release both our pretrained Nemotron 3 Nano 30B-A3B Base and post-trained Nemotron 3 Nano 30B-A3B checkpoints on Hugging Face.