PANews reported on May 7th that Tether AI's research team released the medical language model QVAC MedPsy, which can run locally on low-computing-power devices such as smartphones and wearables without relying on the cloud. The official statement claims that the 1.7B parameter model achieved an average score of 62.62 in seven closed medical benchmark tests, 11.42 points higher than Google MedGemma-1.5-4B-it, and outperformed MedGemma 27B in clinical scenarios such as HealthBench Hard. The 4B version scored 70.54 in the same tests, outperforming competitors with a scale approximately seven times larger, while reducing the average number of tokens generated by one-third to one-half compared to comparable systems, lowering inference costs and latency. The model offers a GGUF quantized version, with Q4_K_M recommended at approximately 1.2GB (1.7B) and 2.6GB (4B), for deployment in privacy- and latency-sensitive scenarios such as hospital local systems and mobile devices.