shoehorn

notactuallytreyanastasio.github.io · 2026-08-21 · by Long Nguyen ·generic
Quantize a BF16 GGUF with an imatrix to exactly fit your VRAM, then run it with llama.cpp. Every spare megabyte spent where it buys the most quality.

shoehorn

Before you download

What fits your machine?

Pick your hardware and this page scans Hugging Face's most-downloaded models for ones shoehorn can fit to your budget — ranked by the quality your memory affords. Runs entirely in your browser.

Your machine

Conversation room

Usable GPU memory, GiB

Find models

Get shoehorn

Install

shoehorn needs llama.cppon your PATH as the inference backend (the Homebrew install pulls it in for you). Then `shoehorn ui` opens the local app — pick a model, press one button, chat.

`brew install notactuallytreyanastasio/shoehorn/shoehorn`Copy

macOSApple SiliconDownload →

Linuxx86-64 · NVIDIA or AMDDownload →

Windowsx86-64 · NVIDIADownload →

Or from source: `cargo install --path .`after cloning the repo. All releases.

The app

One button, your whole budget

The local web app measures your machine, streams the fit, renders the budget as a tape measure, puts a perplexity number on what the fit cost, and ends at a Chat button.

a finished fit: the tape-measure budget gauge at 99.998% used, the per-type mix, and Chat and Measure buttons the discovery card: models ranked by what your budget affords, each with a Use button

notactuallytreyanastasio.github.io · 2 images · 5 links

Comments (0)

No comments yet