TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.
☆101Apr 30, 2026Updated 2 weeks ago
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:
- A collection of stotras, with a compiled book PDF and individual PDFs☆14May 10, 2026Updated last week
- The Best AI Tools☆22May 8, 2026Updated last week
- Hermes skill package for WorldOSINT headless + Polymarket + MiroFish simulation workflows