# gguf-mcp

> gguf-mcp — arose26-gguf-mcp. Use this tool when you need to inspect and analyze local GGUF and safetensors model files without loading their data. It provides metadata, tensor information, and VRAM estimates, and allows for natural-language queries about model architecture, quantization, and compatibility. Ideal for use cases where model analysis and debugging are required, such as optimizing model performance or troubleshooting compatibility issues.

Canonical page: https://skillsregistry.net/skills/arose26-gguf-mcp  
JSON: https://api.skillsregistry.net/v1/skills/arose26-gguf-mcp

## Description

Provides tools to inspect local GGUF and safetensors model files, returning metadata, tensor info, and VRAM estimates without reading tensor data. Enables asking natural-language questions about model architecture, quantization, size, and compatibility.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ck7jeeb4o7)
- **Repository:** <https://github.com/arose26/gguf-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "arose26-gguf-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/arose26-gguf-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/arose26-gguf-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt