Compare AI models

Specifications
Parameters
4B30B
Context window
128k1M
API pricing
Cheapest input
—$0.06Nebius
Cheapest output
—$0.24Nebius
—$24.00Nebius · fp8
Benchmarks
AIME 2025
46.3%89.06%
GPQA Diamond
55.1%73.04%
Overview
CompanyNVIDIANVIDIA
Release dateMay 20 2025Dec 15 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3 Nano leads Llama Nemotron Nano 4B v1.1 on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 209 days before Nemotron 3 Nano, so benchmark comparisons should account for the intervening progress.

Llama Nemotron Nano 4B v1.1 has 4B parameters, while Nemotron 3 Nano has 30B. Context windows are 128k (Llama Nemotron Nano 4B v1.1) vs 1M (Nemotron 3 Nano).

On AIME 2025, Nemotron 3 Nano leads at 89.06% vs Llama Nemotron Nano 4B v1.1 at 46.3%. On GPQA Diamond, Nemotron 3 Nano leads at 73.04% vs Llama Nemotron Nano 4B v1.1 at 55.1%.