nemotron-3-nano

nvidia-open30B

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

Context
262K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Infrastructure
Streaming
Fine-tuning

Details

Provider Ollama
Creator NVIDIA
Family—
Licensenvidia-open
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters30B
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-nano

nemotron-3-nano

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

Changes · 4 entries
nemotron-3-nanoupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesfine tuningyes
nemotron-3-nanoupdate2b100acMar 23, 2026, 05:30 AM
capabilitiestool callyesreasoningyes
descriptionNemotron-3-Nano is a new Standard for Efficient, Open, an...
release_date2025-12-15
parameters30
page_urlhttps://ollama.com/library/nemotron-3-nano
taglineNemotron-3-Nano is a new Standard for Efficient, Open, an...
context_window262144
licensenvidia-open
open_weightyes
tools["function_calling"]
reasoning_tokensyes
modalitiesinput["text"]output["text"]
nemotron-3-nanoupdate7a4f1f6Mar 22, 2026, 05:43 AM
model_typechat
nemotron-3-nanocreate7f5c66fMar 21, 2026, 05:16 AM