NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Intelligence
24.3
#217/523
Coding
19
#219/429
Math
91
#21/265
Speed
114 tok/s
TTFT: 1.38s
Pricing
$0.06 / $0.24
per 1M tokens (in/out)
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is NVIDIA’s model designed for advanced reasoning tasks. It processes at 113.938 tokens per second and is priced at $0.06 per million input tokens, targeting professional users.
When to Use NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
✓ Best For
- Complex mathematical calculations
- Data analysis and interpretation
- Coding assistance and debugging
✗ Not Ideal For
- Basic conversational AI tasks
- High-speed real-time applications
How NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) Compares
Intelligence Index · Higher is better
OpenAIMiniMaxNVIDIAGoogleMBZUAI Institute of Foundation Models
Benchmark Profile
Coding Index
AlibabaPrime IntellectNVIDIAxAIInclusionAI
Output Speed · tok/s
GoogleNVIDIAOpenAIDeepSeek
Math Index
AnthropicAlibabaNVIDIAOpenAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 24.3 | |
| Coding Index | 19 | |
| Math Index | 91 | |
| MMLU-Pro | 794% | |
| GPQA | 757% | |
| LiveCodeBench | 741% | |
| HLE | 102% | |
| SciCode | 29.6% | |
| IFBench | 71.1% | |
| LCR | 33.7% | |
| TerminalBench Hard | 13.6% | |
| Tau2 | 40.9% | |
| AIME 2025 | 91% |
Data: Artificial Analysis · Updated: March 26, 2026
Frequently Asked Questions (15)
When was NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) released?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) was released on December 15, 2025.
Who created NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) was created by NVIDIA.
How intelligent is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) scores 24 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 15).
How fast is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generates output at 169.7 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight models of similar size (median: 97.3 t/s).
What is the latency of NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has a time to first token (TTFT) of 1.74s (based on the median across providers serving the model), which is better than average compared to other open weight models of similar size (median: 1.84s).
How much does NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) cost?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.06 per 1M input tokens (very competitive, median: $0.20) and $0.24 per 1M output tokens (better than average, median: $0.60), based on the median across providers serving the model.
What is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) API pricing?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.06 per 1M input tokens and $0.24 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.10 per 1M tokens. Pricing may vary by provider.
How verbose is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
When evaluated on the Intelligence Index, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generated 140M output tokens, which is at the higher end compared to other open weight models of similar size (median: 19M).
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) a reasoning model?
Yes, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) support?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) supports text input.
What output modalities does NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) support?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) supports text output.
Can NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) process images?
No, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) does not support image input. It can only process text.
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) multimodal?
No, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is not multimodal. It only supports text input.
What is the context window of NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has a context window of 1.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) open source?
Yes, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
