BeClaude

Rapid-MLX

New
2.7kGitHubGeneralby raullenchai

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Install & Usage

1
Create the skills directory
mkdir -p .claude/skills
2
Download the skill file
mkdir -p .claude/skills && curl -o .claude/skills/rapid-mlx.md https://raw.githubusercontent.com/raullenchai/Rapid-MLX/main/SKILL.md
3
Invoke in Claude Code
/rapid-mlx
View source on GitHub
testingapi

Frequently Asked Questions

What is Rapid-MLX?

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

How to install Rapid-MLX?

To install Rapid-MLX, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /rapid-mlx.

What is Rapid-MLX best for?

Rapid-MLX is a community categorized under General. It is designed for: testing, api. Created by raullenchai.