Kakao's multimodal AI language model, 'Kanana-v,' has recorded 1.6 million downloads on the global open-source AI platform Hugging Face. According to Kakao on July 9, the open-source vision-language model (VLM) 'Kanana-1.5-v-3b-Instruct' was downloaded 380,000 times on Hugging Face in the past month alone, with cumulative downloads reaching approximately 1.6 million. Over the past month, Kanana-v was downloaded 2.8 times more than Naver Cloud's similarly sized VLM 'HyperCLOVA X-Seed-Vision-Instruct-3B' (about 137,000 downloads) and surpassed the larger 'Exaone-4.5-33B' from LG AI Research (about 247,000 downloads). Kanana-v is officially listed as a supported model on the open-source inference framework 'vLLM,' allowing immediate deployment. Kakao released 'Kanana-1.5-v-3b' in July last year, introduced 'Kanana-v-4b-Hybrid' in January this year, and is currently developing 'Kanana-2.5' after optimizing 'Kanana-2' for agentic AI. A Kakao representative stated that multimodal models play a key role in agentic AI.