NVIDIA

NVIDIA: Nemotron 3 Super (free)

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models. The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified. Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.

Context Window
262K tokens
Parameters
120B
Input Price
Free
Output Price
Free
Price Tier
budget
Provider
NVIDIA

How to Use NVIDIA: Nemotron 3 Super (free)

With CoreAI, you can start chatting with NVIDIA: Nemotron 3 Super (free) instantly — no separate subscription needed. CoreAI bundles access to NVIDIA: Nemotron 3 Super (free) along with 300+ other AI models from NVIDIA and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select NVIDIA: Nemotron 3 Super (free) from the model selector
  3. Start chatting, comparing, or creating with AI

More NVIDIA Models

NVIDIA

NVIDIA: Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in compl
262K budget
NVIDIA

NVIDIA: Nemotron 3 Nano 30B A3B (free)

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic
256K budget
NVIDIA

NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic
262K budget
NVIDIA

NVIDIA: Nemotron Nano 12B 2 VL (free)

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It int
128K budget
NVIDIA

NVIDIA: Nemotron Nano 12B 2 VL

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It int
131K budget
NVIDIA

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K cont
131K budget

Try NVIDIA: Nemotron 3 Super (free) Now

Chat with NVIDIA: Nemotron 3 Super (free) and 300+ other AI models — all in one app.

Download App → Try on Web App