gezel Gezel Handboek

Models, tiers, and what runs on this device

Gezel doesn't come with its own AI — it puts your choice of AI to work. That can be a cloud provider (OpenAI, Anthropic, GitHub Copilot) or a model running locally on your own machine. With a local model, your data never leaves the room.

Tiers: matching the model to the job

Models come in sizes, and size matters for what a gezel can be trusted to do alone. Gezel groups them into tiers:

TierSize (in billions of parameters)Good at
tinyunder 5Bquick drafts, simple lookups
small5–12Beveryday chat, focused single tasks
medium12–45Bmulti-step work with tools
large45B and up, localmost roles, unsupervised steps
cloudhosted frontier modelseverything

Every role declares a model floor — the minimum tier it needs to work unsupervised. A reviewer gating your deliverables needs more headroom than a gezel drafting a shopping list, and gezel enforces that automatically.

On this device

Gezel classifies each device as tiny, small, medium, or large from the memory available to local models. Open this page in the app to see the current device.

Installed local models

Gezel runs local models (llama.cpp, MLX, Ollama and friends) alongside cloud providers — the Models catalog in the app shows what fits your machine.

Choosing

You don't have to get this right up front. Set a default provider in Settings, and override it per gezel only when a companion needs something different — a big cloud model for your reviewer, a fast local one for day-to-day chat. Gezel checks each new model's fitness on your hardware before recommending it.

Watch this article as a slideshow