Tether Releases QVAC MedPsy Medical AI Model, Achieves 62.62 Score on 17B-Parameter Version

According to Odaily, Tether AI Research Group released QVAC MedPsy, a medical AI model designed to run locally on smartphones and wearable devices without cloud dependency. The 1.7 billion-parameter version scored 62.62 on seven medical benchmarks, outperforming Google's MedGemma-1.5-4B by 11.42 points despite being half its size. The 4 billion-parameter variant achieved 70.54 average score, surpassing models seven times larger. The model generates approximately 909 tokens per inference, significantly lower than comparable systems at 2,953 tokens, reducing latency and computational costs. QVAC MedPsy includes quantized GGUF versions for mobile and edge device deployment.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments