Nemotron Nano 12B 2 VL (free)
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.
Input
Output
Context
128K
Max Output
128K
Parameters
12B
Technical Specifications
Model TypeVision
Context Window128K
Max Output Tokens128K
Parameters12B
Training Cutoff—
License—
Capabilities
Input Modalities
imagetextvideo
Output Modalities
text
Features
vision
Resources & Links
Estimated GPU Requirements for Nemotron Nano 12B 2 VL (free)
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.