Kimi Linear

Training compute

10²³ FLOP

Parameters

48B

Published

Oct 30, 2025

Kimi Linear is an AI model developed by Moonshot (China), first published in October 2025. It works in the language domain, on tasks such as language modeling/generation, question answering and mathematical reasoning.

Training it took an estimated 10²³ FLOP of compute (estimation method: operation counting). The model has 48,000,000,000 parameters. It was trained on roughly 5.7T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Moonshot
Country of organization: China
Domain: Language
Task: Language modeling/generation, Question answering, Mathematical reasoning
Training compute: 10²³ FLOP
Compute estimation method: Operation counting
Parameters: 48,000,000,000
Dataset size: 5.7T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident