Qwen2.5-VL-7B

Training compute

9.9×10²³ FLOP

Parameters

7B

Published

Feb 19, 2025

Qwen2.5-VL-7B is an AI model developed by Alibaba (China), first published in February 2025. It works in the language, vision and multimodal domain, on tasks such as visual question answering, video description, language modeling/generation and 4 more.

Training it took an estimated 9.9×10²³ FLOP of compute (estimation method: operation counting). The model has 7,000,000,000 parameters.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Qwen2.5-7B. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Alibaba
Country of organization: China
Domain: Language, Vision, Multimodal
Task: Visual question answering, Video description, Language modeling/generation, Translation, Question answering, Character recognition (OCR), Quantitative reasoning
Training compute: 9.9×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 7,000,000,000
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: Qwen2.5-7B
Epoch confidence: Confident