NVIDIA: Nemotron Nano 12B 2 VL

By Nvidia

Released: 2025-10-28

Visit Website

API

LLM

RAG

Nvidia

Paid

New

Nvidia Nemotron Nano 12B V2 Vl, developed by NVIDIA, features 12B parameters and 131k-token context window. 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 modelling 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 optimised 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. Available at $0.2/1M tokens.

Specifications

AI Evaluation