Step Edge was launched, with on-device Agent tool calls as fast as 0.1 seconds

robot
Abstract generation in progress
ME AI news, according to Beating Insight monitoring, Jietiao Xingchen has released the on-device model family Step Edge, including the base model, Audio, GUI, and Gen, for endpoints such as mobile phones and automobiles. It can process text, images, and audio locally to perform screen understanding, speech recognition, interface operations, and image generation. The on-device tool-call latency is as low as 0.1 seconds. Simple, high-frequency, or weak-network tasks can be completed locally, while complex reasoning is handled by the cloud. Sensitive data does not need to be uploaded, reducing reliance on networks and cloud compute power. Jietiao has also rolled out its own Step Inference NPU inference engine, designed to reduce latency for terminal chips. The official claims that the Step Edge series ranked first in 29 core evaluation metrics. (Source: MLion)
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned