Offline models

Offline models run entirely on your machine. Download once, use forever, free - and nothing you type ever leaves your computer.

The catalog

Offline Models lists a curated catalog with filters - coding, reasoning, agentic, writing, math, vision - and sort options. Each variant shows its download size, parameters, context window, quantization, and memory needs, plus the fit verdict for your machine:

• Green - fits fully on your graphics card. Fast.
• Yellow - partly on the processor. Works, slower.
• Red - too big for this device.

Licensed models (like MedGemma, Google's medical model) add a short agree-to-the-publisher's-terms step in the download flow.

Beyond the catalog

Add Custom Model from Hugging Face takes any GGUF model URL. The System Information block shows your RAM, GPU, VRAM, and the models directory.

Managing models

Pause a model to hide it from pickers without deleting it. Deleting a model that an AI uses tells you which AIs are affected and what happens to them. Downloads resume if interrupted and survive navigating away.

Health stays home

Health questions route to your device's models by policy, even when routing is otherwise allowed online - and with MedGemma installed, lab results and scans can be read entirely on-device. It helps you understand and prepare questions for your doctor; it never diagnoses.