← Back to Leaderboard
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.
⭐
2.1K
Stars
🍴
269
Forks
👥
26
Contributors
💚
76
Health Score
Star History
Not enough data for chart
Health Score Breakdown
Star Momentum
0
Commit Frequency
100
Issue Health
80
Contributors
91
Release Cadence
100
Documentation
100
Community Signal
100
Project Info
- Language
- Python
- License
- Apache-2.0
- Last Commit
- 15h ago
- Last Release
- v0.6.35 (15h ago)
- Open Issues
- 26
- Bus Factor
- 2
- Commits/Week
- 30.4
- Avg Issue Close
- 4.9 days
apple-siliconclaude-codecursordeepseekfastapihacktoberfestinferencellmlocal-llmm1m2m3macosmlxollama-alternativeopenai-apipython
Project Badge
Embed a live health badge in a README or docs page.
[](https://www.ai-tools-scout.com/projects/rapid-mlx)Compare Rapid MLX
See how this project stacks up against other inference tools.
Weekly AI open-source movers
Get the fastest-growing projects, useful MCP servers, and technical reads in one weekly email.