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)

https://ift.tt/VDeCcoz

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/8PIOR9E