Tether AI 发布 VisionPsy-Nano：边缘设备上的先进视觉语言模型
原标题：VisionPsy-Nano: State-of-the-Art On-Device Vision-Language Models
AI 摘要
Tether AI Research 发布了 VisionPsy-Nano 系列紧凑型视觉语言模型（约 460M 参数），专为边缘设备设计，包含质量优先的 460M 和延迟优化的 460M-Flash 两个版本。该系列在 17 项基准测试中的 16 项上优于同类 ~0.5B 模型，并在推理、视觉感知等能力上超越更大模型。模型以 Apache 2.0 协议开源，支持 Transformers、llama.cpp 和 vLLM 三种推理路径，旨在推动端侧多模态 AI 应用。
正文节选
- Compact VLMs built for the edge: Tether AI Research introduces VisionPsy-Nano, a family of compact (~460M-parameter) vision-language models (VLMs) purpose-built for on-device and edge deployment. It ships as two variants: VisionPsy-Nano-460M (tuned for quality) and VisionPsy-Nano-460M-Flash (tuned for latency), bringing multimodal understanding that used to require the cloud onto the phone in your pocket. - Best-in-class at ~0.5B: VisionPsy-Nano-460M compares favorably to every other ~0.5B VLM