JEV-27B-VL

What is JEV-27B-VL

JEV-27B-VL is a multimodal vision-language model with 27B parameters that supports image understanding and text interaction.

Key features

• Multimodal vision-language model based on 27B parameters
• Supports image understanding and text interaction
• Achieves 61.5% on the ERQA embodied reasoning benchmark (with thinking)
• Enables embodied reasoning without requiring robot or embodiment data

Who it is for

Suitable for researchers and developers needing visual-language understanding, embodied reasoning or multimodal decision-making.

How to get started

1. Visit https://huggingface.co/autotrust/JEV-27B-VL
2. Download the model weights and load them using the standard Qwen/VL method

Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.