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
stableConfidence
highSignal Scores
| Signal | Normalized | Weight | Contribution | Freshness |
|---|---|---|---|---|
Capabilities capability | 66.7 | 30% | 20.0 | 2026-09-22T14:20:54.738Z |
Pricing pricing_tier | 99.8 | 25% | 25.0 | 2026-09-22T14:20:54.738Z |
Context Window context_window | 86.0 | 15% | 12.9 | 2026-09-22T14:20:54.738Z |
Recency recency | 81.5 | 15% | 12.2 | 2026-09-22T14:20:54.738Z |
Output Capacity output_capacity | 85.9 | 15% | 12.9 | 2026-09-22T14:20:54.738Z |
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
| Capability | Supported |
|---|---|
| Vision | No |
| Reasoning | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Function Calling | Yes |
| Web Search | No |
Pricing
Input / 1M tokens
$0.05
Output / 1M tokens
$0.20
Context Window
262K
Max Output
236K