Nemotron Nano 2 Models by NVIDIA AI
6 models2025Up to 4k ctxFrom $0.04/1M input
Details
ResearcherNVIDIA AI
LicenseLlama 3 Community
Commercial useCommercial use: conditional
Models6
Released2025
Max context4k
Capabilities
Vision2 of 6 models
Multimodal2 of 6 models
Structured Outputs2 of 6 models
Links
WebsiteAbout
Second generation Nemotron Nano with Hybrid Transformer-Mamba architecture
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
6 in view
Nemotron-Nano-12B-v2-VLCurrent
Use when the workload needs 12B parameters, structured outputs, and multimodal inputs.
2025-1012B parametersstructured outputsmultimodal inputs
Nemotron-Nano-9B-v2Current
Use when the workload needs 9B parameters and structured outputs.
2025-089B parametersstructured outputs
Use when the workload needs 4k context and 4B parameters.
2025-044k context4B parameters
Use when the workload needs 4k context and 8B parameters.
2025-034k context8B parameters
Use when the workload needs 4k context, 8B parameters, and multimodal inputs.
2025-034k context8B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Nemotron-Nano-12B-v2-VL | Use when the workload needs 12B parameters, structured outputs, and multimodal inputs. | 2025-10 | 12B parametersstructured outputsmultimodal inputs | Current |
| Nemotron-Nano-9B-v2 | Use when the workload needs 9B parameters and structured outputs. | 2025-08 | 9B parametersstructured outputs | Current |
| Nemotron-Nano-12B-v2 | Use when the workload needs 12B parameters. | 2025-08 | 12B parameters | Current |
| Llama 3.1 Nemotron Nano 4B v1.1 | Use when the workload needs 4k context and 4B parameters. | 2025-04 | 4k context4B parameters | Current |
| Llama 3.1 Nemotron Nano 8B v1 | Use when the workload needs 4k context and 8B parameters. | 2025-03 | 4k context8B parameters | Current |
| Llama 3.1 Nemotron Nano VL 8B v1 | Use when the workload needs 4k context, 8B parameters, and multimodal inputs. | 2025-03 | 4k context8B parametersmultimodal inputs | Current |
Release Timeline
4 release groups2025-10
1 current
Nemotron-Nano-12B-v2-VL
Current12B parametersstructured outputsmultimodal inputs
2025-08
2 current
Nemotron-Nano-12B-v2
Current12B parameters
Nemotron-Nano-9B-v2
Current9B parametersstructured outputs
2025-04
1 current
Llama 3.1 Nemotron Nano 4B v1.1
Current4k context4B parameters
2025-03
2 current
Llama 3.1 Nemotron Nano 8B v1
Current4k context8B parameters
Llama 3.1 Nemotron Nano VL 8B v1
Current4k context8B parametersmultimodal inputs
Specifications(6 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Structured Outputs |
|---|---|---|---|---|---|---|
| Nemotron-Nano-12B-v2-VL | 2025-10 | — | 12B | Yes | Yes | Yes |
| Nemotron-Nano-9B-v2 | 2025-08 | — | 9B | No | No | Yes |
| Nemotron-Nano-12B-v2 | 2025-08 | — | 12B | No | No | No |
| Llama 3.1 Nemotron Nano 4B v1.1 | 2025-04 | 4k | 4B | No | No | No |
| Llama 3.1 Nemotron Nano 8B v1 | 2025-03 | 4k | 8B | No | No | No |
| Llama 3.1 Nemotron Nano VL 8B v1 | 2025-03 | 4k | 8B | Yes | Yes | No |
Available From(3 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Nemotron-Nano-9B-v2 | OpenRouter | $0.04 | $0.16 | Serverless |
| Nemotron-Nano-9B-v2 | Vercel AI Gateway | $0.06 | $0.23 | Serverless |
| Nemotron-Nano-12B-v2-VL | OpenRouter | $0.2 | $0.6 | Serverless |
| Nemotron-Nano-12B-v2-VL | Vercel AI Gateway | $0.2 | $0.6 | Serverless |
Popular comparisons in this family
- Llama 3.1 Nemotron Nano 4B v1.1 vs Llama 3.2 NV RerankQA 1B v254
- Llama 3.1 Nemotron Nano 4B v1.1 vs Nemotron Mini 4B Instruct51
- Hunyuan Hy3 Preview vs Llama 3.1 Nemotron Nano VL 8B v149
- Llama 3.1 Nemotron Nano VL 8B v1 vs Llama 2 7B49
- GPT-1 vs Llama 3.1 Nemotron Nano VL 8B v146
- Llama 3.1 Nemotron Nano VL 8B v1 vs Llama 3.2 NV RerankQA 1B v244
- Llama 3.1 Nemotron Nano 8B v1 vs Marin 8B Instruct44
- Llama 3.1 Nemotron Nano 4B v1.1 vs Phi-4 Mini Flash Reasoning35
- Llama 3.1 Nemotron Nano VL 8B v1 vs Llama 3.1 Swallow 8B Instruct30
- Llama 3.1 NemoGuard 8B Content Safety vs Llama 3.1 Nemotron Nano 4B v1.129
Frequently Asked Questions
- What is Nemotron Nano 2 used for?
- Nemotron Nano 2 is used for vision and multimodal work and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does Nemotron Nano 2 compare to NVIDIA Nemotron Nano 12B v2 VL?
- Nemotron Nano 2 by NVIDIA AI is strongest where you need vision and multimodal work, while NVIDIA Nemotron Nano 12B v2 VL by NVIDIA AI is the closest related family to check for structured outputs. Nemotron Nano 2 has 6 listed variants and reaches up to 4k context, so compare the specs and pricing tables before choosing a production model.
- Which Nemotron Nano 2 model should I use?
- For the lowest listed input price, start with Nemotron-Nano-9B-v2 through OpenRouter at $0.04/1M input tokens. For the most capable/latest local choice, evaluate Nemotron-Nano-12B-v2-VL with structured outputs and multimodal inputs.
Related Model Families
Models(6)
Nemotron-Nano-12B-v2-VL
2025-1012B3 providers
MultimodalOpen Weights
Nemotron-Nano-9B-v2
2025-089B3 providers
Open Weights
Nemotron-Nano-12B-v2
2025-0812B
Open Weights
Llama 3.1 Nemotron Nano 4B v1.1
2025-044k4B1 provider
Open Weights
Llama 3.1 Nemotron Nano 8B v1
2025-034k8B1 provider
Open Weights
Llama 3.1 Nemotron Nano VL 8B v1
2025-034k8B1 provider
MultimodalOpen Weights