Live Demo Agent Trial
Live Demo Agent Trial Log In Sign Up
News Wire / technology

Xiaomi Releases Large Open-Source Models

Mastodon Beijing 19d13d Impact 5
Xiaomi has officially unveiled its new MiMo-V2.5 series of Large Language Models (LLMs). This release marks a significant expansion of the company's artificial intelligence capabilities. The rollout follows a period of intense competition in the generative AI sector. Xiaomi has released MiMo-V2.5 with 310 billion parameters and MiMo-V2.5-Pro with 1.02 trillion parameters. Both models feature 1 million token context windows, hybrid attention, and native multimodal capabilities.

Topics

artificial intelligence LLM Xiaomi

Developing

  1. 862d Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore.
  2. 862d Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
  3. 862d Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est.
  4. 862d Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium.

Sources · 7 independent

Mastodon

“Xiaomi unveiled the MiMo-V2.5 series overnight, addi... what really bugs me about conferences of the last decade or so is the strong in-crowd flavour”

Mastodon

“Xiaomi releases MiMo-V2.5 (310B params) and MiMo-V2.5-Pro (1.02T params) as open-source models. Both support 1M token context, hybrid attention, and native multimodal capabilities.”

Unlock the full story

Get a Pro subscription or above to see the live story progression and the full list of independent sources confirming each event as they happen.

Log in to upgrade