Skip to content

Nemotron 3 Nano 30B A3B

by NVIDIARank #344Score 40.0

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

Performance Overview

Score
40.0
Rank
#344
24h Change
0
7d Change
0
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
66.730%20.02026-09-22T14:20:54.738Z
Pricing
pricing_tier
99.825%25.02026-09-22T14:20:54.738Z
Context Window
context_window
86.015%12.92026-09-22T14:20:54.738Z
Recency
recency
81.515%12.22026-09-22T14:20:54.738Z
Output Capacity
output_capacity
85.915%12.92026-09-22T14:20:54.738Z

Top Drivers

positive
Pricing
$0.20/M output tokens
$0.20
positive
Capabilities
Supports reasoning, tools, JSON mode, streaming
4/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 236K output tokens per request
236K

Capabilities

CapabilitySupported
VisionNo
ReasoningYes
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.05
Output / 1M tokens
$0.20
Context Window
262K
Max Output
236K

Related Models

Related

Nemotron 3 Nano 30B A3B Tracker - Performance History | LM Market Cap