Xiaomi Releases Large Open-Source Models
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
Developing
- 890d Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore.
- 890d Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
- 890d Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est.
- 890d 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