kapi models ollama

$ kapi ollama

Detect, inspect, and feed the local Ollama runtime kapi uses for on-device (GPU-accelerated) translation. Ollama itself is a one-time install from https://ollama.com; kapi drives the rest: kapi models ollama pull <model> installs a model, and kapi translate --provider ollama --model <model> uses it.

Commandmodels ollama

Watch it

models ollama needs network access, an API key, or local system access, so it can’t run in the browser playground.See the guides for a recorded run, or try it locally with the installed CLI.

Flags

Flag	Type	Default	Description
--url	string		Ollama server URL (default $OLLAMA_HOST or http://localhost:11434)

← Back to the Command Reference