Tether Data, the AI research arm of the company behind the USDT stablecoin, has released VisionPsy-Nano, a 460-million-parameter vision-language model designed to run locally on smartphones while topping benchmarks for models in its size class. The model was published on July 29, 2026, under a permissive Apache 2.0 license through the company's QVAC research initiative, positioning it as one of the more capable small multimodal models available for on-device use.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.