gguf-vision-check

Community

Check GGUF vision support for multimodal models.

AuthorcrycriM
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps engineers determine whether a GGUF model includes vision input support, and if a separate mmproj vision encoder exists in the same HuggingFace repo, enabling correct multimodal deployment with llama.cpp.

Core Features & Use Cases

  • Vision support detection: identify vision-related keys and tensors in the main GGUF and locate any accompanying mmproj files.
  • Repository validation: assess HuggingFace repo listings to confirm a mmproj file is present for VL-capable models.
  • Use Case: accelerate setup of multimodal inference pipelines by ensuring both main GGUF and the vision mmproj are available before serving.

Quick Start

Use this skill to verify a local GGUF file's vision support and locate its mmproj companion.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gguf-vision-check
Download link: https://github.com/crycriM/hermes-skills/archive/main.zip#gguf-vision-check

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.