Skip to content
raullenchai avatar

Trending repo

Claude Code & Cursor rules for Rapid-MLX

by @raullenchai · 2,101 stars · Python

View on GitHub →

About 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.

Rapid-MLX Run AI on your Mac. Faster than anything else. Run local AI models on your Mac — no cloud, no API costs. Works with Cursor, Claude Code, and any OpenAI-compatible app. pip install → serve Gemma 4 26B → chat + tool calling → works with PydanticAI, LangChain, Aider, and more. | | Your Mac | Model | Speed (tok/s = words/sec) | What works | |:---|:---:|:---:|:---:|:---:| | **16 GB** MacBook Air | Qwen3.5-4B | 160 tok/s | Chat, coding, tools | | **32+ GB** Mac Mini / Studio | Nemotron-Nano 30B | 141 tok/s | 🆕 Fastest 30B, 100% tools | | **32+ GB** Mac Mini / Studio | Qwen3.6-35B | 95 tok/s | 256 experts, 262K context | | **64 GB** Mac Mini / Studio | Qwen3.5-35B | 83 tok/s | Best balance of smart + fast | | **96+ GB** Mac Studio / Pro | Qwen3.5-122B | 57 tok/s | Frontier-level intel

Topics

apple-siliconclaude-codecursordeepseekfastapihacktoberfestinferencellmlocal-llmm1m2m3

No rules target Rapid-MLX yet

No published rules, MCP servers, or skills target Rapid-MLX yet. If you maintain a tool that works well with this project, you can publish for free during beta.

Why this page exists

RuleSell tracks the AI-coding ecosystem so you don't have to. When a repo like Rapid-MLX picks up momentum, we surface the Claude Code skills, Cursor rules, MCP servers, and agent configs that target it — with real author attribution, SPDX license badges, and quality scores. Every listing ships with copy-paste install for each environment.