Devstral-Small-Vision-2505-GGUF Open Source Model - Supports Image and Text Generation, Compatible with llama.cpp Framework

Devstral Small Vision 2505 GGUF

Developed by ngxson

Vision encoder based on Mistral Small model, supports image-text generation tasks, compatible with llama.cpp framework

Downloads 777

Release Time : 5/21/2025

Model Overview

A language model integrated with visual encoding capabilities, capable of processing image inputs and generating relevant textual descriptions

Visual Encoding Capability

Integrated Mistral Small vision encoder for image understanding

llama.cpp Compatibility

Optimized for llama.cpp framework, enabling seamless deployment

Multimodal Processing

Capable of processing both visual and textual inputs to generate coherent outputs

Image Understanding

Text Generation

Multimodal Reasoning

Content Generation

Image Caption Generation

Automatically generates descriptive text based on input images

As shown in examples, can accurately describe image content and scenes

Assistive Tools

Visual Question Answering

Answers user questions based on image content

Property	Details
Model Type	image-text-to-text
Base Model	mistralai/Devstral-Small-2505

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base