# LFM2.5-local

> Use this tool when you need to run AI models locally for privacy and speed, and integrate with other tools like Claude Desktop and Cursor. LFM2.5-local solves problems of slow inference and data privacy by providing fast and secure processing on Mac devices. It takes in text inputs and outputs chat responses, ideal for use cases requiring local AI processing and multi-device clustering.

Canonical page: https://skillsregistry.net/skills/wispayr-lfm2-5-local  
JSON: https://api.skillsregistry.net/v1/skills/wispayr-lfm2-5-local

## Description

Run Liquid AI's LFM2.5 model locally on Mac with a chat UI and MCP server for integration with Claude Desktop, Cursor, and other tools. Offers fast inference, privacy, and multi-Mac clustering.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qtgrk3yuiz)
- **Repository:** <https://github.com/WispAyr/LFM2.5-local>

## 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": "wispayr-lfm2-5-local"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wispayr-lfm2-5-local` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wispayr-lfm2-5-local/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