NEWSUPDATE: Moonshot's Kimi K2 uses a 1T-parameter MoE architecture with 32B active parameters and outperforms models like GPT-4.1 and DeepSeek-V3 on key benchmarks (Michael Nuñez/VentureBeat)

Sunday, 13 July 2025

Moonshot's Kimi K2 uses a 1T-parameter MoE architecture with 32B active parameters and outperforms models like GPT-4.1 and DeepSeek-V3 on key benchmarks (Michael Nuñez/VentureBeat)

Michael Nuñez / VentureBeat:
Moonshot's Kimi K2 uses a 1T-parameter MoE architecture with 32B active parameters and outperforms models like GPT-4.1 and DeepSeek-V3 on key benchmarks — Moonshot AI, the Chinese artificial intelligence startup behind the popular Kimi chatbot, released an open-source language model on Friday …

from Techmeme https://ift.tt/djLDUmI

No comments:

Post a Comment

thanks for message

Subscribe to: Post Comments (Atom)