Jian Zhang

Today we're releasing Nemotron 3 Nano Omni. Audio, Video, Image, Text ➡️ Text Ask questions about all your data. Amazing efficiency powered by the Nemotron Hybrid SSM MoE architecture. State of the art multimodal intelligence.

@huggingface Nemotron 3 Super is now a leading reasoning foundation for @OpenClaw 🦞 and complex agentic workflows, with 1.5M+ downloads in its first two weeks. 🤗 huggingface.co/nvidia/NVIDIA-…

Golden time for open model coalitions. We are in a mission to open all our data, infra and research to the ecosystem! @NVIDIAAI @nvidia Come and join us for the Nemotron open model Journey! Checkout our recent research on PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost: arxiv.org/abs/2603.21383

🚀 Introducing Nemotron-Cascade 2 🚀 Just 3 months after Nemotron-Cascade 1, we’re releasing Nemotron-Cascade 2: an open 30B MoE with 3B active parameters, delivering best-in-class reasoning and strong agentic capabilities. 🥇 Gold Medal-level performance on IMO 2025, IOI 2025, and ICPC World Finals 2025: • Capabilities once thought achievable only by frontier proprietary models (e.g. Gemini Deep Think) or frontier-scale open models (i.e. DeepSeek-V3.2-Speciale-671B-A37B). • Remarkably high intelligence density with 20× fewer parameters. 🏆 Best-in-class across math, code reasoning, alignment, and instruction following: • Outperforms the latest Qwen3.5-35B-A3B (2026-02-24) and even larger Qwen3.5-122B-A10B (2026-03-11). 🧠 Powered by Cascade RL + multi-domain on-policy distillation: • Significantly expand Cascade RL across a much broader range of reasoning and agentic domains than Nemotron-Cascade 1, while distilling from the strongest intermediate teacher models throughout training to recover regressions and sustain gains. 🤗 Model + SFT + RL data: 👉 huggingface.co/collections/nv… 📄 Technical report: 👉 research.nvidia.com/labs/nemotron/…

🚀 NVIDIA Nemotron 3 Super is now available on Together AI. A 120B hybrid MoE model with 12B active parameters, delivers leaing efficiency and accuracy for multi-agent AI systems. Run Nemotron 3 Super on Together’s Dedicated inference with reliable infrastructure and 99.9% SLAacross coding, reasoning, and agentic pipelines production workloads.

@NVIDIAAI @ArtificialAnlys

Nemotron 3 Super is live! So far the most intelligent agentic reasoning model in the Nemotron family, with world leading efficiency and openness. Super particularly marks our first infra & research milestone in agentic reinforcement learning scaling up. Stay tuned for more infra, data and agentic generalization research we will open to the ecosystem. 🤗 Huggingface: lnkd.in/gWfamwwX 📜 Tech Report: lnkd.in/gRFFJxKm 🤸‍♂️NeMo-Gym (RL env data and orchestration): github.com/NVIDIA-NeMo/Gym 🤸NeMo-RL (RL training): github.com/NVIDIA-NeMo/RL

Announcing NVIDIA Nemotron 3 Super! 💚120B-12A Hybrid SSM Latent MoE, designed for Blackwell 💚36 on AAIndex v4 💚up to 2.2X faster than GPT-OSS-120B in FP4 💚Open data, open recipe, open weights Models, Tech report, etc. here: research.nvidia.com/labs/nemotron/… And yes, Ultra is coming!

🔍 Super is inside Perplexity for Pro & Max users now! Lets surf the web.

🦞 Super is the #1 open model in PinchBench for OpenClaw. pinchbench.com Watch out and it could pinch you.

Nemotron 3 Super is here — 120B total / 12B active, Hybrid SSM Latent MoE, designed for Blackwell. Truly open: permissive license, open data, open training infra. See analysis on @ArtificialAnlys Details in thread 🧵below:

NVIDIA has released Nemotron 3 Super, a 120B (12B active) open weights reasoning model that scores 36 on the Artificial Analysis Intelligence Index with a hybrid Mamba-Transformer MoE architecture We were given access to this model ahead of launch and evaluated it across intelligence, openness, and inference efficiency. Key takeaways ➤ Combines high openness with strong intelligence: Nemotron 3 Super performs strongly for its size and is substantially more intelligent than any other model with comparable openness ➤ Nemotron 3 Super scored 36 on the Artificial Analysis Intelligence Index, +17 points ahead of the previous Super release and +12 points from Nemotron 3 Nano. Compared to models in a similar size category, this places it ahead of gpt-oss-120b (33), but behind the recently-released Qwen3.5 122B A10B (42). ➤ Focused on efficient intelligence: we found Nemotron 3 Super to have higher intelligence than gpt-oss-120b while enabling ~10% higher throughput per GPU in a simple but realistic load test ➤ Supported today for fast serverless inference: providers including @DeepInfra and @LightningAI are serving this model at launch with speeds of up to 484 tokens per second Model details 📝 Nemotron 3 Super has 120.6B total and 12.7B active parameters, along with a 1 million token context window and hybrid reasoning support. It is published with open weights and a permissive license, alongside open training data and methodology disclosure 📐 The model has several design features enabling efficient inference, including using hybrid Mamba-Transformer and LatentMoE architectures, multi-token prediction, and NVFP4 quantized weights 🎯 NVIDIA pre-trained Nemotron 3 Super in (mostly) NVFP4 precision, but moved to BF16 for post-training. Our evaluation scores use the BF16 weights 🧠 We benchmarked Nemotron 3 Super in its highest-effort reasoning mode ("regular"), the most capable of the model's three inference modes (reasoning-off, low-effort, and regular)

there you go for GTC

NVIDIA GTC 2026 takes place March 16–19 in the heart of Silicon Valley—San Jose, CA. It’s my favorite AI event of the year, bringing together cutting-edge research and real-world business implementation (THE HARDWARE DEMOS on the show floor is a must see!!!). I’ll be speaking about Nemotron post-training on March 17, and there will be many more exciting talks, sessions, and demos throughout the week. Virtual attendance is free and you can get 25% off for in-person pass, using my employee code: nvidia.com/gtc/?ncid=GTC-… to save 25% on your conference pass.

🚨Nemotron 3 Nano on LM Arena! Come and give it a try!

Thank you @percyliang for the insights and support. Excited to release all the open artifacts to the whole ecosystem and community. Looking forward to the next Marin as well.

NVIDIA has just released Nemotron 3 Nano, a ~30B MoE model that scores 52 on the Artificial Analysis Intelligence Index with just ~3B active parameters Hybrid Mamba-Transformer architecture: Nemotron 3 Nano combines the hybrid Mamba-Transformer approach @NVIDIAAI has used on previous Nemotron models with a moderate-sparsity MoE architecture, enabling highly efficient inference, particularly at longer sequence lengths Small-model improvements: with 31.6B total and 3.6B active parameters, Nemotron 3 Nano scores 52 on our Intelligence Index, in line with OpenAI’s gpt-oss-20b (high). This represents a +6 point lead on the similarly-sized Qwen3 30B A3B 2507 and +15 improvement on NVIDIA’s previous Nemotron Nano 9B V2 (a dense model) High openness: Nemotron 3 Nano follows other recent NVIDIA models in open licensing and releases of data and methodology for the community to use and replicate - it scores an 67 on the Artificial Analysis Openness Index, in line with previous Nemotron Nano models Key model details: ➤ 1 million token context window, with text only support ➤ Supports reasoning and non-reasoning modes ➤ Released under the NVIDIA Open Model License; the model is freely available for commercial use or training of derivative models ➤ On launch, the model is being made available with a range of serverless inference providers including @baseten, @DeepInfra, @FireworksAI_HQ, @togethercompute and @friendliai, and it is available now on Hugging Face for local inference or self-deployment See below for our full analysis and key announcement links from NVIDIA 👇

NEWS: NVIDIA announces the NVIDIA Nemotron 3 family of open models, data, and libraries, offering a transparent and efficient foundation for building specialized agentic AI across industries. Nemotron 3 features a hybrid mixture-of-experts (MoE) architecture and new open Nemotron pretraining and post-training datasets, paired with NeMo Gym, an open-source reinforcement learning library that enables scalable, verifiable agent training. Read more: nvda.ws/4oNUTBm