marzukia/qMLX

qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS layer duplication for efficient large-model serving on consumer hardware.

30

Stars

1

Forks

29.0

Radar Score

Stable

Momentum

Scoring Breakdown

Impact9.5

Velocity37.2

Health48.9

Growth Metrics

7-Day Stars

+0

30-Day Stars

+0

Acceleration

x

Language

Python

Why it ranks

Steady growth — consistently collecting stars and contributors.

Local AITop 85% globally