skills.rest
tdimino
tdiminoCOMMUNITY
Explore all skills by this author →
Website𝕏@IdaeanDaktylGitHub

smolvlm

Analyze images locally and answer visual questions with SmolVLM-2B.

41|3|Updated Jan 2, 2026
Search Tags:#ocr#vision#image analysis#local model#vqa#smolvlm
One-click install
npx skills add https://github.com/tdimino/claude-code-minoan --skill smolvlm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: smolvlm
Source: https://github.com/tdimino/claude-code-minoan/tree/main/skills/design-media/smolvlm
Command: npx skills add https://github.com/tdimino/claude-code-minoan --skill smolvlm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mlx-vlm, and includes scripts (resource) components.

What problem does it solve?

This Skill enables local, on-device image analysis without relying on cloud services, ensuring privacy and faster processing for visual tasks.

Core Features & Use Cases

  • Local Image Analysis: Utilizes SmolVLM-2B for image understanding directly on your machine.
  • Versatile Prompts: Supports general descriptions, specific text extraction (OCR), UI analysis, and visual question answering.
  • Use Case: Quickly get a description of a screenshot, extract text from a receipt image, or ask questions about the content of a photograph without uploading it.

Quick Start

Use the smolvlm skill to describe the image located at /path/to/image.png.

Frequently Asked Questions about smolvlm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from an image locally on macOS?▼

Local image analysis extracts text from images directly on your device using the SmolVLM-2B model. It operates offline without uploading files to cloud services, ensuring privacy and faster processing for visual tasks.

Can I perform visual question answering without an internet connection?▼

Visual question answering can be performed entirely offline using local models. This Skill processes image interpretation and answers specific queries about visual content on-device without relying on an internet connection.

Does local image analysis with SmolVLM work on Windows or Linux?▼

Local image analysis with SmolVLM is exclusive to macOS with Apple Silicon. It requires the mlx-vlm Python package to run the 2B model, meaning Windows and Linux environments are currently unsupported.

How do I analyze a screenshot and get a detailed description on my machine?▼

To analyze a screenshot locally, provide the image file path to the Skill. It uses the SmolVLM-2B model to generate detailed image descriptions and UI analysis directly on your machine without cloud processing.

What is the best way to run a local vision model for OCR and image understanding?▼

The best way to run a local vision model for OCR and image understanding is using the mlx-vlm framework. It enables the SmolVLM-2B model to perform versatile prompts including text extraction and UI analysis on macOS Apple Silicon.

Do I need Python to use SmolVLM for on-device image interpretation?▼

You need Python to use SmolVLM for on-device image interpretation because the Skill depends on the mlx-vlm Python package. This package provides the necessary environment to run the SmolVLM-2B model locally.

Related Skills

Explore More Design & Creative Skills→
PicoMLXPicoMLX
24

swift-mlx-lm

Run local LLM and VLM inference on Apple Silicon using MLX in Swift.

Official
Advanced
twjarviszyra-webtwjarviszyra-web
3

clip

Classify images and match visual content to text labels.

Community
Intermediate
cabeznocabezno

ocr-and-documents

Extract text and markdown from PDFs and scanned files via OCR.

Community
Intermediate
techczechtechczech

text-to-image

Generate images locally on Apple Silicon with MLX-native diffusion models.

Community
Advanced