3 Matching Annotations
  1. Last 7 days
  2. apple.github.io apple.github.io
    https://apple.github.io/ml-pico/
    1
    1. fxp007 24 May 2026
      on an iPhone 17 Pro Max, it encodes 12MP images as fast as 230ms, and decodes them in 150ms

      这些具体的编码和解码时间数据表明PICO在实际设备上的运行速度非常快，230ms编码和150ms解码的时间对于移动设备处理12MP图像来说非常高效。这一数据点与大多数需要高端GPU运行的ML编码器形成鲜明对比，增强了其实用性。

      data-point runtime-performance mobile-device
    Visit annotations in context

    Tags

    Annotators

    URL

    apple.github.io/ml-pico/
  3. Apr 2026
  4. developer.nvidia.com developer.nvidia.com
    https://developer.nvidia.com/blog/bringing-ai-closer-to-the-edge-and-on-device-with-gemma-4/
    1
    1. fxp007 08 Apr 2026
      The E4B and E2B are the newest edition of on-device and mobile designed models first launched with Gemma 3n.

      大多数人认为移动设备上的AI模型需要大幅简化功能才能高效运行。但作者暗示Gemma 4的E4B和E2B版本在移动设备上仍然保持了多模态能力，包括文本、音频、视觉和视频处理，这挑战了移动AI能力的传统认知。

      non-consensus mobile-ai on-device
    Visit annotations in context

    Tags

    Annotators

    URL

    developer.nvidia.com/blog/bringing-ai-closer-to-the-edge-and-on-device-with-gemma-4/
  5. Apr 2020
  6. vocalishealth.com vocalishealth.com
    Vocalis Health
    1
    Visit annotations in context

    Tags

    Annotators

    URL

    vocalishealth.com/