LLM Reference

Nemotron 3 Super-120B-A12B

About

120B MoE model with 12B active parameters - hybrid Mamba-Transformer with Multi-Token Prediction for agentic workflows

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
NVIDIA NIMServerless

Rankings

Specifications

Released2026-03-11
Parameters120B
Context1M
ArchitectureDecoder Only
Specializationgeneral

Providers(1)