Nemotron Nano 12B V2 VL

Nemotron Nano 12B V2 VL is a model from NVIDIA. 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.

On the Respan gateway, Nemotron Nano 12B V2 VL costs $0.20 per 1M input tokens and $0.60 per 1M output tokens on Bedrock, after gateway discounts.

Nemotron Nano 12B V2 VL is served by Bedrock.

Nemotron Nano 12B V2 VL accepts up to 128K tokens of context.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "nemotron-nano-12b-v2-vl". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Nemotron Nano 12B V2 VL has 7 published benchmark scores, including DocVQA 94.4% and AI2D 87.1%. Each score links to where it was published; the data is collected by Respan.