skills.rest
yankeeinlondon
yankeeinlondonCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

model-citizen

Inventory and manage local LLM models across Ollama, LM Studio, and Llama.cpp.

3|Updated Jan 10, 2026
Search Tags:#cli#llm#rust#huggingface#model-management#gguf#model-citizen
One-click install
npx skills add https://github.com/yankeeinlondon/rusty-biscuit --skill model-citizen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-citizen
Source: https://github.com/yankeeinlondon/rusty-biscuit/tree/main/.claude/skills/model-citizen
Command: npx skills add https://github.com/yankeeinlondon/rusty-biscuit --skill model-citizen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Model Citizen unifies discovery, organization, and management of local LLM models across Ollama, LM Studio, and Llama.cpp, providing a consistent workflow for model metadata, sharing, and CLI access.

Core Features & Use Cases

  • Consolidated model discovery across multiple runtimes with consistent metadata
  • Rich enrichment from GGUF headers, config values, and HuggingFace repos
  • Use Case: inventory and compare models by size, architecture, and licensing to streamline deployment

Quick Start

List local models with metadata using the model CLI.

Frequently Asked Questions about model-citizen

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

FAQPage Schema
How do I manage local LLM models across Ollama, LM Studio, and Llama.cpp from a single CLI?▼

You can inventory, organize, and manage local LLM models across Ollama, LM Studio, and Llama.cpp using a unified CLI workflow that consolidates model discovery and metadata into a single consistent interface.

Can I compare local GGUF models by size, architecture, and licensing for deployment?▼

Yes, you can compare local GGUF models by size, architecture, and licensing. The tool enriches model metadata by extracting data from GGUF headers, config values, and HuggingFace repositories to streamline deployment decisions.

Does this model management CLI work with MLX models as well as GGUF files?▼

Yes, the model management CLI supports deploying, sharing, and maintaining both GGUF and MLX models across multiple runtimes, including Ollama, LM Studio, and Llama.cpp, within your development environment.

What is the best way to inventory local LLM models installed across different runtimes?▼

The best way to inventory local LLM models is using a consolidated CLI workflow that discovers models across multiple runtimes and applies consistent metadata enrichment from GGUF headers and HuggingFace repos.

Why use a unified CLI for local LLM model management instead of individual runtime interfaces?▼

A unified CLI provides consistent model metadata and organization across Ollama, LM Studio, and Llama.cpp, solving the problem of fragmented discovery and management when maintaining multiple local LLM models across different runtimes.

Related Skills

Explore More Software Engineering Skills→
afel6afel6

gguf-quantization

Convert and quantize transformer models into GGUF format for CPU inference.

Community
Advanced
afel6afel6

serving-llms-vllm

Deploy LLM serving with vLLM and OpenAI-compatible endpoints.

Community
Advanced
iani-kuliiani-kuli

huggingface-best

Query HuggingFace leaderboards to recommend models fitting hardware memory constraints.

Community
Intermediate
ovachieverovachiever
52

llama-cpp

Run LLM inference on CPU and non-NVIDIA hardware with GGUF quantization.

Community
Advanced