Thread

1. nateb2022 · 1790790715 · focus · HN ↗

   Any source on the benchmarks/methodology besides the image? There's a ton of variance possible in llama.cpp's performance depending on how it was configured. I'd also like to see benchmarks against MLX.

   1. anerli · 1790792439 · focus · HN ↗

      Compared to MLX - we've done some rough benchmarking and we are outperforming any of the MLX-based engines we've compared to so far. Going to do more in depth benchmarking and release it soon.

Unofficial Hacker News client; not affiliated with Y Combinator.