NVIDIANVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
- Released
- Dec 15, 2025
- Tracked since
- 2026-07-23
Intelligence index8.9Ranks 412 of 664 models with this metric
Coding index14.4Ranks 219 of 259 models with this metric
Agentic index1Ranks 133 of 156 models with this metric
Capability profile
5 axes vs. site averageNVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Site average
Pricing
per 1M tokens- Input
- $0.050
- Output
- $0.200
- Cache read
- $0.050
Performance
- Output throughput
- 195 tokens/sec
- Time to first token
- 1.11s
- First answer token
- 11.35s
- End-to-end response
- 13.91s
History
2Intelligence index
14.2→8.9
Output
Unchanged across 62 days of records
Output throughput
150→195
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−50% - Granite 4.2 3B
IBMIntelligence 9.1$0.120−40% - Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−25% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−25%
- Sarvam 105B (high)SarvamIntelligence 8.8$0.170−15%