Qwen2.5-VL 72B Instruct

qwen

Qwen vision-language model for visual reasoning, documents, and agent tasks

Family: qwen
Providers: 1
Context: 131,072
Output: 8,192
Knowledge: 2024-04
Weights: Open
Input: textimage
Output: text
Release date: 2024-09
Updated: 2024-09

Providers

Source: models.dev