Smoldocling 256M Preview Mlx Fp16
This model is converted from ds4sd/SmolDocling-256M-preview to the MLX format, supporting image-text-to-text tasks.
Downloads 24
Release Time : 3/17/2025
Model Overview
SmolDocling-256M-preview-mlx-fp16 is a vision-language model based on the MLX framework, primarily used for image-text-to-text tasks. It is converted from the original model ds4sd/SmolDocling-256M-preview and optimized for efficient operation on Apple silicon.
Model Features
MLX format optimization
The model has been converted to the MLX format, making it particularly suitable for efficient operation on Apple silicon.
Vision-language processing
Supports image-text-to-text tasks, capable of understanding and generating text content related to images.
Lightweight model
With a parameter size of 256M, it is suitable for deployment and use in resource-constrained environments.
Model Capabilities
Image-text understanding
Text generation
Vision-language task processing
Use Cases
Document processing
Image document parsing
Extract text information from images and generate structured text.
Multimodal applications
Image caption generation
Generate descriptive text based on input images.
Featured Recommended AI Models