Engines / defai-digital / ax-engine

ax-engine
Runs Qwen 3.8 27B with AXQ quantization and MTP on MLX for Apple M5.
Benchmarks
- On M5 Max 128GB, table 7.5.3 with Qwen 3.8 27B (AXQ 6-bit MTP), it decodes at 76.04 tok/s, against 27.92 tok/s for mlx-lm (2.7×), and it reads prompts at 768.7 tok/s. 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Something wrong or out of date?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.