TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
NVIDIA
Models
Nemotron 3 Super

Nemotron 3 Super

By NVIDIA
Nemotron 3 Super is released as a 12B-active, 120B-total parameter hybrid MoE model that introduces LatentMoE for accuracy, multi-token prediction layers for faster inference, and NVFP4 pretraining, with support for up to 1M context length and published checkpoints plus training datasets.
New Text Gen 7
Released: March 11, 2026

Overview

Nemotron 3 Super is NVIDIA’s open Mixture-of-Experts hybrid Mamba-Transformer model designed for high-throughput agentic workloads and long-context reasoning.

🤖Agents📚Large Language Models🔍Advanced reasoning💻Conversational coding

About NVIDIA

Industry: Computer Hardware Manufacturing
Company Size: 36000
Location: Santa Clara, California, US
Website: nvidia.com
View Company Profile

Tools using Nemotron 3 Super

Related Models

  • Gen 7
    Glyph
    Glyph is a symbol-aware language model for code and math. It emphasizes structured reasoning, tool use, and precise formatting, returning JSON, diffs, and proofs or derivation steps that are easy to verify.
    🇯🇵Japanese lessons📚Code explanations💻Coding📋Task management
    Text
    Released 5mo ago
  • Gen 7
    GNMT
    GNMT, Google Neural Machine Translation, is Google’s end-to-end neural system for Translate. It replaced phrase-based MT with an encoder-decoder LSTM plus attention, uses subword units to handle rare words, and applies beam search with length control for fluent, accurate translations at scale.
    Text
    Released 9y ago
  • Gen 7
    ERNIE 4.5 VL 28B A3B Thinking
    A multimodal MoE model that “looks, reads, and reasons” across images, video, and text. It adds tool use and a Thinking with Images mode, supports long context, and activates about 3B parameters per token for flagship-level VLM quality at practical latency.
    📷Images💻Coding👤Avatars🎥Videos
    Text
    Released 4mo ago
Last updated: March 12, 2026
0 AIs selected
Clear selection
#
Name
Task