88Z AI, 13 July — StepFun has released Step Edge, an on-device model suite for terminals like phones and cars, covering base, audio, GUI, and generation models. With native cloud-edge synergy, it achieves 0.1s low local latency and full-modal privacy protection, ranking first in 29 core benchmarks across text-vision, audio, GUI, and image generation.
At a glance
- Step Edge supports 0.1s ultra-low local latency and full-modal privacy protection
- Ranked first in text-vision, audio, GUI, and image generation across 29 core benchmarks
The update
StepFun has officially launched Step Edge, an on-device model suite designed for terminals such as smartphones and automobiles. The product line is comprehensive, covering four main directions: base models, Audio, GUI, and Gen, aiming to fully address various on-device scenarios. Technically, Step Edge adopts a native cloud-edge synergy architecture, which not only ensures privacy protection for all modal data but also reduces local latency to 0.1 seconds, guaranteeing extreme response speeds. In terms of performance, the series demonstrates strong capabilities in 29 core benchmarks, achieving first place in key dimensions including text-vision understanding, audio processing, graphical user interface interaction, and image generation, highlighting its leading position in on-device AI.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 阶跃StepFunSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.