NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is a text-based AI model by NVIDIA. It features 176 tok/s output speed, $0.06/1M input tokens pricing. It scores 24.3 on the intelligence index.
Strengths
- +Fast output speed (176 tok/s)
- +Very affordable pricing ($0.06/1M tokens)
Benchmarks
Intelligence24.3Coding19.0Math91.0
MMLU-Pro
0.8
GPQA
0.8
LiveCodeBench
0.7
Intelligence
24.3
Coding
19.0
Math
91.0
Output Speed
176 tok/s
Latency (TTFT)
0.72s
Blended Price
$0.10/M
Pricing per 1M Tokens
| Input (Prompt) | $0.06 |
| Output (Completion) | $0.24 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) with:
Alternatives to NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
More from NVIDIA
Frequently Asked Questions
How much does NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) cost?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) costs $0.06/1M input tokens and $0.24/1M output tokens.
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) good for coding?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) has a lower coding score of 19.0. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) generates output at 176 tok/s. Time to first token is 0.72s.
Is there a free version of NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
No, NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
Last updated: