The Tether AI Research Group has launched the QVAC MedPsy series of medical language models, designed to run locally on low-power devices such as smartphones and wearables, reducing dependence on cloud infrastructure. According to the official announcement, the 1.7B parameter version achieved an average score of 62.62 across seven closed medical benchmarks, outperforming Google’s MedGemma-1.5-4B-it; the 4B version scored an average of 70.54, surpassing larger models including MedGemma-27B-text. Tether states that the model also reduces inference costs and is available in quantized GGUF versions for local deployment.
Tether Launches On-Device Medical AI Model QVAC MedPsy
TechFlowShare
Summary
Tether announced on-chain news: the QVAC MedPsy series of medical AI models is now available for on-device use. Built on TechFlow, the models run locally on smartphones and wearables, reducing reliance on the cloud. The 1.7B parameter version scored 62.62 across seven medical benchmarks, outperforming MedGemma-1.5-4B-it. The 4B version achieved 70.54, surpassing MedGemma-27B-text. Tether also released a quantized GGUF version for local deployment, lowering inference costs. This AI and crypto update underscores Tether’s expansion into edge AI applications.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.