a pretty practical idea for people who run models locally and are tired of playing guess the gguf. the tradeoff is that packing memory tightly is not the same thing as deciding whether the resulting model is actually worth chatting with.
Shoehorn
Make any language model fit your machine
6 ratings4.24
Saves97
CategoryDeveloper Tools
PlatformWeb
PricingFree
Shoehorn quantizes language models to exactly fit the available VRAM of your hardware, optimizing memory usage while maintaining quality and enabling efficient run with llama.cpp. It includes a local web app for easy model selection and chat interaction.
ai
Ratings & Reviews
Write a reviewInformation
CategoryDeveloper Tools
PlatformsWeb
PricingFree
AccountNot confirmed
ListedAugust 2026
WebVisit
Report a problem
Website checks
Mobile PageSpeed
Automated checks of the public website by Google Lighthouse 13.5.0. Scores can vary between runs.
Checked Oct 24, 2026
Test this website on PageSpeedWebsite checks refresh automatically each week.
- Performance
- 100 out of 100, Good
- Accessibility
- 100 out of 100, Good
- Best Practices
- 100 out of 100, Good
- SEO
- 100 out of 100, Good
Around the Web
Show HN97 source points · 16 comments
does this work similar to airllm? i am wondering how it would handle something like quantizing kimi k3 on a budget of 8 gbs, or is that something you are not attempting to solve yet?
mbuchel-hn · Imported from Show HN
tried it out but based on the model sizing result i got i got an insufficient memory error when the server started running
jaylane · Imported from Show HN
This is interesting. I wonder how it could work with something like https://github.com/JustVugg/colibri.
akshay_akula · Imported from Show HN
I gotta laugh at some of the models it suggests, for example: > AnkitAI/Parable-Qwen3-4B-Claude-Fable-5-GGUF you’re telling me you managed to fit Fable 5 into just 4B?
jedbrooke · Imported from Show HN
This is really impressive. Can you say a bit about the underlying process? I'm guessing this is post-training qantization? Isn't PTQ also resource-intensive? (Ie might not work on any machine)
puttycat · Imported from Show HN