nemotron-3-super

open-weight120B

NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

Context
262K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Provider Ollama
Creator NVIDIA
Family—
Licenseopen-weight
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters120B
Architecture—
Context window262K tokens
Max input—
Max output—
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

API

GET/v1/models/ollama/nemotron-3-super

nemotron-3-super

NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

Changes · 4 entries
nemotron-3-superupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesfine tuningyes
nemotron-3-superupdate2b100acMar 23, 2026, 05:30 AM
capabilitiestool callyesreasoningyes
descriptionNVIDIA Nemotron 3 Super is a 120B open MoE model activati...
release_date2026-03-11
page_urlhttps://ollama.com/library/nemotron-3-super
taglineNVIDIA Nemotron 3 Super is a 120B open MoE model activati...
context_window262144
parameters120
licenseopen-weight
open_weightyes
tools["function_calling"]
reasoning_tokensyes
modalitiesinput["text"]output["text"]
nemotron-3-superupdate7a4f1f6Mar 22, 2026, 05:43 AM
model_typechat
nemotron-3-supercreate7f5c66fMar 21, 2026, 05:16 AM