Nemotron Nano 12B 2 VL
nvidia/nemotron-nano-12b-v2-vl
Usage data date 2026-07-27 · updated daily
Usage and specs
What is 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.
Nemotron Nano 12B 2 VL capabilities
Input: Image、Text、Video Output: Text
Nemotron Nano 12B 2 VL API pricing
USD list-price snapshot, not independently verified; confirm current pricing and terms on the provider site before purchase.