2.8-trillion-parameters

#2.8-trillion-parameters

@interjc: The market still needs a disruptive force; whether you use Kimi or not, the major companies' reset cycles are increasing.

X AI KOLs Following ↗ · 7h ago Cached

Kimi releases the K3 model, featuring 2.8 trillion parameters, a million-token context window, and native multimodal capabilities. It leverages Kimi Delta Attention and Attention Residuals to enhance inference speed and training efficiency.

0 favorites 0 likes

2.8-trillion-parameters

@interjc: The market still needs a disruptive force; whether you use Kimi or not, the major companies' reset cycles are increasing.

Submit Feedback