Run a model fully offline

You'll set up the embedded provider so a model runs entirely on your device from local files — no API key, no base URL, no network call.

What you need

A GGUF model file (or several) already downloaded to the device. BYLM never ships a model; you bring the file.
Enough device memory and storage for the model you pick.
On Android, the files in a folder you can grant the app access to.

Open Providers and add a provider of kind Local llama.cpp (embedded). It has no base URL and no API key.

The embedded provider's form — a models-folder field and a compute backend (Vulkan), with no base URL or key

Set the Models directory to the folder holding your .gguf files. On desktop, browse to the folder. On Android, grant a folder through the system file picker. The folder is scanned and each model file becomes selectable.
Optionally choose the Compute backend — Auto lets the engine decide, or set CPU or Vulkan explicitly (ROCm as well, on Linux). It's saved per device and applied the next time a model loads.
Optionally cap Decode threads for CPU generation; leave it empty for an automatic count.
Create an agent, choose this provider, and pick one of the scanned models. Start a conversation — generation runs in-process, on your hardware, with nothing leaving the device.

Keep an embedded agent beside a hosted one. Because you choose the provider per agent, the same app can hold a private local agent and a frontier hosted agent side by side.
Swap backends to trade speed for compatibility — Vulkan (or ROCm on Linux) to use the GPU, CPU as the safe fallback.