NVIDIANVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
- Released
- Oct 28, 2025
- Tracked since
- 2026-07-23
Intelligence index5.8Ranks 576 of 664 models with this metric
Coding index—Not tested
Agentic index—Not tested
Capability profile
5 axes vs. site averageNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
Site average
Some dimensions have no data yet — marked on the chart
Pricing
per 1M tokens- Input
- $0.200
- Output
- $0.600
Performance
- Output throughput
- 207 tokens/sec
- Time to first token
- 1.18s
- First answer token
- 1.18s
- End-to-end response
- 3.59s
History
2Intelligence index
4.6→5.8
Output
Unchanged across 62 days of records
Output throughput
200→207
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Llama 3.1 Instruct 8B
MetaIntelligence 6.9$0.050−92% - Mistral Small 3
MistralIntelligence 6.7$0.080−87% - Gemma 4 E4B (Reasoning)
GoogleIntelligence 8.9$0.100−83% - Gemma 4 E4B (Non-reasoning)GoogleIntelligence 7.5$0.100−83%
- Granite 4.1 8B
IBMIntelligence 6.6$0.100−83%