GGUF · 7 models available

Run a decision model with llama.cpp

GGUF is the format that made local inference ordinary. For decision models it matters more than usual, because the whole argument for the category is cost per call.

How to run it

  1. Install a runtime

    llama.cpp is the reference implementation. Ollama wraps it if you would rather not build anything.

    brew install llama.cpp
  2. Pull a model straight from Hugging Face

    The -hf flag downloads and caches the GGUF without a separate step.

    llama-cli -hf <owner>/<repo>
  3. Watch memory, not disk

    A quantised 400M encoder is a few hundred megabytes on disk and runs comfortably on a laptop. The 2B and larger decoders are where you start caring about RAM.

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.