# local-llm

> local-llm — pakkio-mcp-local-llm. Use this tool when you need to efficiently answer trivial, standalone questions without incurring additional costs, by delegating them to a local AI model. It solves the problem of minimizing paid token usage for simple queries, providing a cost-effective solution. The local-llm tool takes in straightforward questions as input and outputs relevant answers, ideal for use cases where budget optimization is key.

Canonical page: https://skillsregistry.net/skills/pakkio-mcp-local-llm  
JSON: https://api.skillsregistry.net/v1/skills/pakkio-mcp-local-llm

## Description

MCP server that lets Claude Code delegate trivial, standalone questions to a local Gemma 4 model via llama.cpp, saving paid tokens.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/s35ygdm2kf)
- **Repository:** <https://github.com/pakkio/mcp-local_llm>

## 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": "pakkio-mcp-local-llm"
    }
  }
}
```

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