Nvidia Nemotron 3 Super 120B A12B BF16
NVIDIA develops the Nvidia Nemotron 3 Super 120B A 12B NVFP 4, a large language model designed to deliver strong agentic, reasoning, and conversational capabilities, making it well-suited for collaborative agents and high-volume workloads such as IT ticket automation. Its architecture, a LatentMoE - Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction, is a notable technical trait.
Input
Output
Context
262K
Max Output
33K
Parameters
123.6B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens32,768 tokens
Parameters123.6B
Release DateMar 10, 2026
Training CutoffFeb 1, 2026
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
19.2%
HLE
80.0%
GPQA
36.0%
SciCode
31.2
Coding
25.4
Intelligence
155
Speed (tok/s)
14.0
TTFA (s)
1.0
TTFT (s)
Resources & Links
Estimated GPU Requirements for Nvidia Nemotron 3 Super 120B A12B BF16
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.