Tether's QVAC releases open source visual language model VisionPsy Nano

According to the Tether blog, the AI research project QVAC under Tether Data has released VisionPsy Nano, an end-to-end visual language model with approximately 460 million parameters. The model achieved the highest comprehensive normalized score of 62.3 in the visual language model below 500 million parameters, outperforming competitors such as Liquid AI and Hugging Face in 16 out of 17 benchmark tests. Tether has released two versions, both of which are open-source under the Apache 2.0 license. Tether CEO Paolo Ardoino stated that this proves that local first, efficient AI is a viable path to enable powerful and private AI to run on people's existing devices.