arun-prasath

↗ HN profile [ 22.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I wanted to know how fast a 26B mixture-of-experts model could run on a desktop CPU with no GPU. Got ~40 tok/s single-stream (lossless) and ~124 batched. The surprising part was the byte budget: for this model you…