Nemotron Nano 12B 2 VL

About Nemotron Nano 12B 2 VL

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency. The model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension. Nemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost. Open-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

NVIDIA Model Lineup

Compare all models from NVIDIA to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Olmo 3.1 32B Instruct

Allen AI

Input: $0.20

Output: $0.60

Context: 66k

Qwen2.5 VL 32B Instruct

Alibaba Qwen

Input: $0.20

Output: $0.60

Context: 128k

UnslopNemo 12B

Thedrummer

Input: $0.40

Output: $0.40

Context: 1.0M

Llama 3.1 70B Instruct

Meta

Input: $0.40

Output: $0.40

Context: 131k

💡 Cheaper Alternatives

Same Brand (NVIDIA)

Cross Brand

🚀 Quick Start

Get started with Nemotron Nano 12B 2 VL API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nvidia/nemotron-nano-12b-v2-vl",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision