Coral-decider-4b-GGUF
A GGUF build of Coral-decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
Community card
What this is
A repackaged build of Coral-4b, not a separate model. The weights are the same; what changes is the runtime you can put them in and the hardware that will hold them.
How to run it
llama.cpp
GGUF runs on CPU. No Python, no GPU, and no network call in the path of a decision. Full llama.cpp guide.
llama-cli -hf mradermacher/Coral-decider-4b-GGUFA public number is a shortlist, not a decision
The only benchmark that settles which model you ship is one built from your own historical decisions. We freeze that test set, run the candidates against it, and hand back the threshold your error budget supports.