[Edaily Reporter Park Jung-Soo ] #Nota Inc., a company specializing in AI model lightweighting and optimization technologies, has launched an on-device AI optimization competition at the Korea Computer Conference (KCC 2026) to expand its developer ecosystem.

Nota Inc. announced on the 29th that it held the “On-Device AI Optimization Competition with NetsPresso” at KCC Corporation 2026, which took place in Jeju.
This competition was designed to improve the execution efficiency of AI models in on-device environments using Nota Inc.’s AI optimization platform, “NetsPresso.” NetsPresso is a platform that optimizes AI models for various hardware environments, enabling them to run stably even with limited resources.
As generative AI has recently spread to various devices and industrial settings, the importance of software technologies that efficiently run AI models in real-world environments has grown. Nota Inc. explained that through this competition, it provided developers with an opportunity to directly verify the results of AI optimization in actual on-device environments.
Participants undertook performance improvement tasks to make AI models run faster and more efficiently, building upon the basic AI optimization environment provided by Nota Inc.
The championship was won by the “EcoPruner” team from Chung-Ang University, while the Grand Prize went to “Team Iris” from Sungkyunkwan University, and the Excellence Awards were awarded to “DKE” and “Gamjabat,” respectively.
The winning team, “EcoPruner,” proposed an optimization method for efficiently running large language models (LLMs) on small DEVICES. They received high praise for improving response latency per token by approximately 6.7 times, reducing the time to first response by about 4 times, and cutting memory usage by about 85% while maintaining the same level of quality as existing models.
Alongside the competition, Nota Inc. operated a recruitment booth and hosted a special lecture at the KCC Corporation 2026 venue, showcasing real-world industrial applications of AI optimization technology. Through these efforts, the company expanded its engagement with members of the on-device AI ecosystem, including researchers and developers.
Kim Tae-ho, Nota Inc.’s Chief Technology Officer (CTO) and co-founder, stated, “This competition was highly significant because participants were able to directly experience the entire AI optimization process based on Netzpresso and achieve meaningful performance improvements in a real-world execution environment.” He added, “We will continue to support the easy and efficient optimization of AI models across various hardware environments and contribute to the expansion of the on-device AI ecosystem.”