ainewsblitz.com

Breaking

Tether Data Open-Sources VisionPsy-Nano, a 460M On-Device Vision-Language Model Running on Smartphones

Tether Data Open-Sources VisionPsy-Nano, a 460M On-Device Vision-Language Model Running on Smartphones
  • Foundation Models
  • Open Source
  • Media Generation

Tether Data's AI research initiative QVAC has released VisionPsy-Nano, a 460-million-parameter open-source vision-language model designed to run directly on consumer smartphones, claiming best-in-class performance among sub-0.5B models. The model, published on July 29, 2026 under the permissive Apache 2.0 license with open weights, is optimized for on-device and edge deployment and ships in two variants, according to the official announcement.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year