Kimi-VL-A3B-Thinking-6bit Open-source Vision-Language Model - Supports Multilingual Image-to-Text and Text-to-Text Tasks

Kimi VL A3B Thinking 6bit

Developed by mlx-community

Kimi-VL-A3B-Thinking-6bit is a multilingual vision-language model converted based on the MLX format, supporting image-text to text tasks.

Downloads 135

Release Time : 4/17/2025

Model Overview

This model is converted from moonshotai/Kimi-VL-A3B-Thinking and is mainly used for image understanding and text generation tasks.

Multilingual support

Supports text generation and understanding in multiple languages.

Vision-language model

Can handle joint tasks of images and text, such as image description generation.

MLX format

Converted to the MLX format for easy deployment and use in specific environments.

Image description generation

Multilingual text generation

Vision-language understanding

Image understanding

Image description

Generate descriptive text based on the input image.

Generate detailed descriptions related to the image content.

Multilingual applications

Multilingual image description

Supports image description generation in multiple languages.

Generate image description text in the target language.

Property	Details
Pipeline Tag	image-text-to-text
Library Name	transformers
Base Model	OpenGVLab/InternVL3-1B-Instruct
Base Model Relation	finetune
Datasets	OpenGVLab/MMPR-v1.2
Language	multilingual
Tags	internvl, custom_code, mlx

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base