Kalsa
Engines / raullenchai / Rapid-MLX

Rapid-MLX

Apple M1–M6EngineApache-2.0

Builds on mlx-lm to decode Qwen3.5-9B faster than oMLX on Apple Silicon. It is built on ml-explore/mlx-lm.

Benchmarks

  • On M5 Max 36GB with Qwen3.5-9B (4-bit), it decodes at 115.5 tok/s, against 77.9 tok/s for oMLX (+48%). Source

Listing

Listed: Passed all seven checks.

Security review

Not reviewed yet.

Install

To install it, follow the project's own instructions on GitHub. The engine runs with your user's permissions. macOS doesn't sandbox it, so install only engines you trust.

Something wrong or out of date? Write to help@kalsa.io, or ask us to remove this page.