Kimi releases K2 model
Original title:Kimi K2
AI summary
Kimi K2 uses a mixture-of-experts (MoE) architecture with 32 billion activated parameters and 1 trillion total parameters, achieving SOTA performance on frontier knowledge, math and coding tasks among non-reasoning models.
Key Takeaways
- Kimi K2 uses a mixture-of-experts (MoE) architecture with 32 billion activated parameters and 1…
- achieving SOTA performance on frontier knowledge
- math and coding tasks among non-reasoning models.
Quick Facts
- Published
- Updated
- Source
- Moonshot AI:Kimi Blog
- Category
- Other
Why it matters
月之暗面发布 Kimi K2,万亿参数 MoE 架构,多基准 SOTA
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Kimi releases K2 model. July 11, 2025. https://new.nat6.net/en/news/cmnwsdpte002xslagx733du94/