Kalsa
Engines / lablup / mlxcel

mlxcel

Apple M1, M5EngineApache-2.0

Decodes Qwen3-30B-A3B faster than mlx-lm on an M5 Max.

Benchmarks

  • On M5 Max with qwen3-30b-a3b (4-bit), it decodes at 166.55 tok/s, against 143.81 tok/s for mlx-lm (+16%). 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Something wrong or out of date?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.