arozanov / turboquant-mlxView on GitHub
TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.
70Apr 2, 2026Updated this week

Alternatives and similar repositories for turboquant-mlx

Users that are interested in turboquant-mlx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?