🤫husshhussh
🤫husshhusshOnePuppy
🤫 celebrates

Alex Barron

MLX core contributor, quantization and fast kernels

EngineeringmacOS
The work

What we are celebrating, specifically.

  • MLX quantized SDPA
  • 3 and 6 bit quantization in MLX
  • fast Hadamard transform in Metal

Apple

MLX engineer · current

Why

Why we celebrate them.

Alex's quantization work, from quantized attention to 3 and 6 bit weights, is why big models fit on ordinary Macs at all. He does hard numerical engineering in public pull requests where anyone can learn from it.

Sources — their own pages, so you can check us

  • Quantized SDPA PR
  • 3 and 6 bit quantization PR
This page is yours

Alex Barron, this belongs to you.

We built this from your public work because we think it deserves celebrating. You did not ask us to, so the only fair thing is that you decide what happens to it. Claim it and it is yours to edit. Ask us to change something and we will. Ask us to take it down and it is gone within 72 hours — free, no account needed, and nobody will try to talk you out of it.

Claim or remove this pageEveryone we celebrate