| <html lang="en"> | |
| <head> | |
| <meta charset="utf-8" /> | |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> | |
| <title>Rapid-MLX — run local models on your Mac</title> | |
| <meta name="description" content="Run MLX models locally on Apple Silicon with an OpenAI- and Anthropic-compatible server." /> | |
| <link rel="stylesheet" href="style.css" /> | |
| </head> | |
| <body> | |
| <main class="card"> | |
| <h1>Rapid-MLX</h1> | |
| <p>Local OpenAI- and Anthropic-compatible inference for Apple Silicon.</p> | |
| <h2>Run it on your Mac</h2> | |
| <pre><code>curl -fsSL https://rapidmlx.com/install.sh | bash | |
| rapid-mlx serve ling-3.0-tiny-4bit | |
| curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}'</code></pre> | |
| <p class="note">The example needs at least 8 GB unified memory; allow more for long contexts.</p> | |
| <p>Use it from OpenCode / Claude Code / Codex: <code>rapid-mlx agents <name> --setup</code> · <a href="https://rapidmlx.com/docs/agents">Agent setup</a></p> | |
| <nav aria-label="More about Rapid-MLX"> | |
| <a href="https://rapidmlx.com/download">Desktop app</a> | |
| <a href="https://rapidmlx.com/compare">Measured comparison</a> | |
| <a href="https://rapidmlx.com">Website</a> | |
| </nav> | |
| </main> | |
| </body> | |
| </html> | |