jkf87

Openclaw Mlx Setup — Development skill for Claude Code

Development community

One-click setup for running local LLMs (MLX) on Apple Silicon Mac with OpenClaw.

How to install Openclaw Mlx Setup

This entry records only its repository, not the path inside it, so there is no exact command to give. Open jkf87/openclaw-mlx-setup and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Openclaw Mlx Setup does

One-click setup for running local LLMs (MLX) on Apple Silicon Mac with OpenClaw.

Alternatives in Development

Nexting — Remote control for Claude Code, Codex, Grok, and Cursor on Mac or PC 1.3k ★
Skill Manager — Manage skills across Codex CLI, Claude Code, Cursor, OpenCode, and OpenClaw from one local app 117 ★
FlowBoard — Local-first project management and persistent context for OpenClaw, Claude Code, Codex, Cursor, and multi-agen 94 ★

README

OpenClaw + MLX Local Model Setup

One-click setup for running local LLMs on Apple Silicon Mac with OpenClaw

[![Platform](https://img.shields.io/badge/platform-macOS%20Apple%20Silicon-blue)](https://support.apple.com/en-us/116943) [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)

What is this?

This skill automatically sets up a local LLM on your Apple Silicon Mac and connects it to [OpenClaw](https://github.com/nichochar/openclaw). It handles everything:

Detects your Mac's RAM and selects the optimal model
Installs dependencies (mlx-lm)
Downloads the model from HuggingFace
Starts mlx_lm.server (OpenAI-compatible API)
Configures openclaw.json automatically
Tests the connection

Quick Start

# Clone and run
git clone https://github.com/jkf87/openclaw-mlx-setup.git
cd openclaw-mlx-setup
bash scripts/auto_install.sh

That's it. Your OpenClaw agents (Telegram bots, etc.) can now use local models.

Requirements

Item	Requirement
Mac	Apple Silicon (M1/M2/M3/M4)
RAM	8GB minimum
Python	3.10+
OpenClaw	Installed and configured

Auto-Selected Models by RAM

RAM	Model	Size	Use Case
8GB	Qwen3-4B-4bit	~2.5GB	Light chat
16GB	Qwen3-8B-4bit	~4.9GB	Best value
32GB	Qwen3-14B-4bit	~8.5GB	Balanced
64GB+	Qwen3-32B-4bit	~19GB	High performance

Architecture

[HuggingFace MLX Model] --> [mlx_lm.server :8080] --> [OpenClaw] --> [Telegram Bot / Agent]
                             OpenAI-compatible API     mlx provider

Options

# Auto-select model (default)
bash scripts/auto_install.sh

# Specify a model
bash scripts/auto_install.sh --model mlx-community/Qwen3-14B-4bit

# Change port
bash scripts/auto_install.sh --port 8081

# Restart without re-downloading
bash scripts/auto_install.sh --skip-download