AI Briefingdots3-note 280B MoE Released
Key point
dots-studio has released a 280B MoE multimodal model supporting a 512K context window.
Details
dots3-note preview is the first open-weight model in the dots3 product family. It adopts a Mixture-of-Experts (MoE) architecture, with a total of 280B parameters but only 16B parameters activated during inference.
It supports a maximum context length of 512K tokens and features multimodal capabilities, understanding text, images, video, and audio while outputting text.
Key optimization areas include:
- General knowledge and instruction following, mathematical and logical reasoning
- Tool use and multi-step agent workflows
- Code generation and code-based problem solving
- Understanding images, documents, charts, audio, and video
- Long-context information processing
This model is the lightest in the dots3 product family, designed to provide an optimal balance between model capability, latency, and inference cost.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Xiaomi Releases Open-Weight Multimodal Model MiMo-V2.6-Pro… Higher Intelligence and Competitive Pricing Compared to Similar-Sized Models
Ant Group Releases Finance-Specialized Open-Weight Model 'Ling-3.0-flash-Fin'