88Z AI, 14 August — Xiaohongshu's dots model lab has released dots3-note preview, the first open-source version of the dots3 series. With 280B total parameters and 16B activated parameters, it supports a 512K context window and offers multimodal understanding of text, vision, and speech, performing competitively in various benchmarks.
At a glance
- dots3-note preview is the first open-source model in the dots3 series, with 280B total and 16B activated parameters.
- It supports a 512K context window and multimodal understanding of text, vision, and speech, achieving strong benchmark results.
The update
Xiaohongshu's dots model lab has officially open-sourced dots3-note preview, marking the first public release of the dots3 series. Built on a mixture-of-experts architecture, the model features 280B total parameters with 16B activated parameters, efficiently handling context windows up to 512K. Functionally, dots3-note preview integrates multimodal understanding across text, vision, and speech, with specific optimizations for complex reasoning, agent applications, and multimodal perception scenarios. Despite its relatively compact activated parameter size, the model performs comparably to much larger models in various authoritative benchmarks, demonstrating high performance efficiency and technical potential.
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.
- 机器之心Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.