Nemotron Nano 12B V2 VL (free)
Nvidia · text, image → text
Developed by Nvidia, Nemotron-Nano-12B-V2-VL-Free is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It features a powerful 128,000-token context length to handle extensive visual and textual inputs. The model utilizes a hybrid Transformer-Mamba architecture, successfully combining transformer-level accuracy with Mamba's structural advantages.
Input$0.00 /M
Output$0.00 /M