Qwen2.5-14B

Training compute

1.6×10²⁴ FLOP

Parameters

14.7B

Published

Sep 19, 2024

Qwen2.5-14B is an AI model developed by Alibaba (China), first published in September 2024. It works in the language domain, on tasks such as language modeling/generation, question answering and quantitative reasoning.

Training it took an estimated 1.6×10²⁴ FLOP of compute (estimation method: operation counting). The model has 14,700,000,000 parameters.

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

Full record

Organization: Alibaba
Country of organization: China
Domain: Language
Task: Language modeling/generation, Question answering, Quantitative reasoning
Training compute: 1.6×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 14,700,000,000
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident