@AdinaYakup: More players are joining the open source summer RedNote just released dots3-note preview The first open weight model in…
Summary
RedNote has released dots3-note preview, the first open-weight model in the dots3 family, featuring 280B parameters with 16B active, multi-modal understanding (text, image, video, audio), 512K context length, and Apache 2.0 license, with strong agent capabilities.
View Cached Full Text
Cached at: 08/14/26, 07:47 PM
More players are joining the open source summer
RedNote just released dots3-note preview The first open weight model in the dots3 family
- 280B / 16B active
- Text + Image + Video + Audio understanding
- 512K context length
- Apache2.0 licensed
- Strong agent capabilities with tool use & multi step workflows
Similar Articles
@AdinaYakup: RedNote don’t release that often, but each one is solid https://huggingface.co/dots-studio/dots3-note-prev…
dots3-note Preview is a multimodal Mixture-of-Experts AI model with 280B total parameters and 16B activated, supporting up to 512K token context, released as an open-weight model on Hugging Face.
dots-studio/dots3-note-prev · Hugging Face
dots-studio releases dots3-note preview, the first open-weight model in the dots3 family: a 280B-parameter multimodal MoE with 16B activated parameters, 512K context, and support for text, image, video, and audio understanding.
@svpino: Here is the article explaining how dots3-note Preview works: https://studio.dots.ai/dots/dots3-en.html… And here is the…
The article explains how the dots3-note Preview model works and provides a link to try it on OpenRouter for free.
dots3-note Preview targets autonomous agency and dynamic real-world environments with 512K context
dots3-note Preview is an AI model targeting autonomous agency and dynamic real-world environments with a 512K context window.
@AdinaYakup: dots.tts New TTS from Xiaohongshu (RedNote) 2B - Apache 2.0 Fully continuous architecture (no codec tokens) 48kHz synth…
Dots.tts is a new TTS model from Xiaohongshu (RedNote) with 2B parameters, Apache 2.0 license, fully continuous architecture without codec tokens, 48kHz synthesis, and zero-shot voice cloning.