Nemotron Nano v2 VL 12B

Overview

NVIDIA's 12.6B enterprise VLM with strong DocVQA and ChartQA scores, tuned for professional document extraction workflows.

When to pick this model

• Enterprise document extraction and DocVQA pipelines
• Chart and table understanding at production scale
• Single-GPU multimodal deployments
• Long-context multimodal tasks up to 128k tokens

VRAM requirements by quantization

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

• Combined vision and text in a 12B footprint
• 128k context window
• Strong DocVQA and ChartQA benchmark scores
• NVIDIA Open Model license

Limitations

• Trails Qwen3-VL 30B on complex visual reasoning
• NVIDIA license terms differ from Apache or MIT
• Smaller community than Qwen or LLaVA families

Architecture & training

Architecture: Dense vision · 12.6B · Nemotron-Nano-v2 VL · 128k context

Training: NVIDIA Nemotron Nano v2 multimodal — text + images in 12B.

Quick start

ollama run nemotron3-v2:12b

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.