Fri, Aug 14 04:04 PM

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

Hacker News•Fri, Aug 14, 2026, 02:43 PM•2 min read

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 working for such a large...

Source: [Hacker News](https://github.com/notactuallytreyanastasio/shoehorn)

📰 Read Full Story

This is an aggregated headline summary. For the complete report, visit the original publisher.

Continue Reading at Hacker News ↗

#tech #made #running #show #shoehorn #library #quantize #llm #fit

More Headlines

TechnologyHacker News• 3m ago

AI: The Devil on My Shoulder

1 points, 0 comments on Hacker News

TechnologyHacker News• 3m ago

Deferred Token Response

1 points, 0 comments on Hacker News

TechnologyZDNet• 4m ago

Dell XPS 13 review: The first budget laptop to rival Neo raises the bar for all PCs

The Dell XPS 13 flaunts build quality rarely seen at this price point, but not without trade-offs.

TechnologyHacker News• 4m ago

Hours of Jingling Keys [video]

1 points, 0 comments on Hacker News

TechnologyZDNet• 4m ago

ChatGPT's new Computer History tracks your Mac activity to create a timeline - but should you let it?

Rolling out to ChatGPT's Mac app, Computer History creates a timeline from your activities across the apps and websites you use on your Mac. Is that a privacy risk?

TechnologyGitHub Blog• 4m ago

How to bring your software delivery workflow into GitHub with agent apps

See how four GitHub Agent Apps can help you scope, secure, roll out, and ship a feature across the SDLC–all without leaving GitHub. The post How to bring your software delivery workflow into GitHub with agent apps appeared first on The GitHub Blog .