Show HN: Shoehorn, a library to quantize an LLM to fit your Mac's VRAM

By rhgraysonii · 2026-08-14 · 6 points · 0 comments

https://github.com/notactuallytreyanastasio/shoehorn

I made this after seeing someone posit the idea online yesterday over lunch then spent some time refining it. So far it's pretty impressive IMO! Right now I am running Qwen3-30B-A3B on my 24gb unified memory m4 MacBook Pro at 50 tok/sec and this should definitely not be wor…

Open the full discussion on BetterNews