Tether Releases Open-Source Medical AI Model That Runs on Phones and Laptops
Tether said it released QVAC MedPsy, an open-source medical AI model family designed to run directly on smartphones, laptops and servers instead of relying on cloud processing. The company said the models support GGUF formats, are built for edge devices and emphasize user privacy.
Tether said QVAC MedPsy 4B outperformed MedGemma 27B, while QVAC MedPsy 1.7B beat MedGemma 4B in clinical-style evaluations including HealthBench Hard, HealthBench and MedXpertQA. The company also said the models reduce response tokens by 3.2 times, improving efficiency on consumer hardware.
From the sources (3 posts)
@tetherTether Unveils Medical AI That Runs on Phones, Outperforms Much Larger SoTA Models, and Can Cut the Cloud Out Entirely Read more:
@tether8 billion humans deserve an intelligence that doesn't blink when the signal dies. 🧠 Introducing @QVAC Psy, our foundational models built on the mathematical stability of Psychohistory. With QVAC MedPsy, our local-first medical health AI mo
@paoloardoinoWe just released our QVAC MedPsy, Tether AI SoTA medical health AI model, capable of high-performance execution and high-accuracy directly on smartphones, laptops and servers. Highlights: - QVAC MedPsy 4B beats MedGemma 27B - QVAC MedPsy 1