by NVIDIA
Nemotron-3-120B-Super is a large language model (LLM) developed by NVIDIA, featuring 120 billion parameters. It is part of the Nemotron-3 family of models designed for high-performance text generation, synthetic data generation, and enterprise applications. The model is optimized for use in data centers and cloud environments, leveraging NVIDIA's advanced GPU infrastructure. It supports a wide range of natural language processing (NLP) tasks, including but not limited to text generation, summarization, translation, and code generation. Nemotron-3-120B-Super is particularly notable for its use in generating synthetic data to train other AI models, which can help address data scarcity and privacy concerns in AI development. NVIDIA Nemotron-3-Super-120B-A12B-BF16 is a 120B-parameter (12B active) Latent Mixture-of-Experts (LatentMoE) hybrid model (Mamba-2 + MoE + Attention) with Multi-Token Prediction (MTP). It is optimized for agentic workflows, long-context reasoning (up to 1M tokens), tool use, and RAG, and is commercially usable under the NVIDIA Nemotron Open Model License. The model excels in math, code, science, and multilingual tasks, and is designed for high-volume workloads like IT ticket automation.
Complete information about the vendor/provider of this AI application
Discover EU-based alternatives for this AI application.
Track, assess, and govern your AI applications with Anove.
1 considerations identified
Review recommended before use
These considerations are automatically identified based on publicly available information about the vendor and AI catalog data. Actual risks may vary based on your specific use case and implementation.
Visual representation of the vendor's digital supply chain relationships
Third-party vendors and subprocessors used by this vendor
Legal, privacy, and compliance documentation
Get insights into risk by running assessments on this AI application.
Types of data commonly processed by this application
