Tether AI Releases 460 Million Parameter Vision Language Model Optimized for Edge Devices
Tether AI released VisionPsy-Nano, an open-source vision-language artificial intelligence model with 460M parameters. The model is built to process images and text directly on phones and laptops without requiring cloud connectivity.
The company states the architecture achieved the highest overall benchmark scores in its weight class. The launch follows a separate software development kit update and a preview of the edge-optimized model posted earlier this week.
From the sources (7 posts)
@paoloardoinoTether AI gonna release a SOTA AI model optimized for edge devices in the next few days.
@paoloardoinoTether AI new SDK release
@tetherRT @paoloardoino: Tether AI gonna release a SOTA AI model optimized for edge devices in the next few days.
@tetherTether Data Open-Sources VisionPsy-Nano: Best-in-Class ~460M On-Device Vision-Language Model Leading Industry Benchmarks Learn more:
@paoloardoinoTether AI just released VisionPsy, a best-in-class state-of-the-art vision language model optimized for edge devices (phones, laptops, ...) with the highest overall score in its class/weight 🤖
@paoloardoinoTether AI's new SOTA vision model for edge devices, live benchmarked against other models in the same class 👑
@paoloardoinoRT @qvac: Today we release VisionPsy-Nano: state-of-the-art vision-language models at 460M parameters, built to run on-device. It leads ev…