by 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.
| Signal | Strength | Weight | Impact |
|---|---|---|---|
| Recency2026-03-03T20:29:33.174Z | 100 | 15% | +15.0 |
| Capabilities2026-03-03T20:29:33.174Z | 57 | 25% | +14.3 |
| Context Window2026-03-03T20:29:33.174Z | 81 | 15% | +12.2 |
| Versatility2026-03-03T20:29:33.174Z | 67 | 10% | +6.7 |
| Output Capacity2026-03-03T20:29:33.174Z | 20 | 10% | +2.0 |
| Pricing Tier2026-03-03T20:29:33.174Z | 1 | 25% | +0.2 |
Cost Estimator
You save $37.59/month vs category average