Seoul: NC AI, an artificial intelligence affiliate of game giant NCSOFT Corp., announced the release of its new Korean-based multimodal AI model as open source. The company revealed that the four models of VARCO-VISION 2.0-14B, 1.7B, 1.7B OCR, and Video-Embedding-are now accessible for free for commercial purposes.

According to Yonhap News Agency, VARCO-VISION 2.0 represents a next-generation AI model that possesses the capability to understand both images and text simultaneously to answer questions. The model can analyze multiple images concurrently, making it particularly effective in processing complex documents, tables, and charts. It also provides a natural understanding of both Korean and English, with enhanced comprehension of Korean culture.

NC AI has claimed that the 14B model surpasses other open-source counterparts, such as InternVL3-14B, Ovis2-16B, and Qwen2.5-VL 7B, in various benchmarks. These include English and Korean image understanding and optical character recognition (OCR).

NC AI CEO Lee Yeon-soo commented on the release, stating, “With the release of these four models, NC AI, which has been leading Korea’s multimodal AI market in specialized fields such as media, games, and fashion, has demonstrated its potential to uphold Korea’s sovereignty in the vision-language AI domain.”