modelbenchmark.io

nemotron-3-nano:30b

NVIDIA · nemotron-3-nano

Compare

Small Nemotron 3 MoE for efficient coding, math, and long-context agents

Specification

most-agreed values

Context
1M
Max output
131K
Released
2025-12-15
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.06
Output
$0.24

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
ollama-cloud · 30b$0.06$0.241M131K

More from NVIDIA

most-hosted first