Qwen3 4B, for opencode

A local model on llama.cpp. Status: checking… · For agents: /agent

Connect opencode

Once, on your machine (opencode installed with npm i -g opencode-ai):

…

Then run opencode in any folder. opencode and your files stay on your machine; only the model calls come here.

Where m64 is installed, m64 <this capsule> --ui opencode does both steps.

Try the model