Curated local models
Three conversation-first choices: quickest, recommended, and more capable but slower. All three see images, so any of them can do screen vision.
Want a different size, a different family, or a non-vision model? Search Hugging Face for any GGUF from the same screen. See Custom models.
What the catalog tells you about your GPU
What the catalog tells you about your GPU
Before you pick, the catalog reports the GPU it detected and how much graphics memory it has: dedicated VRAM, shared memory, or a plain “graphics memory unavailable” when it cannot tell.That last case is honest rather than reassuring. With no GPU information, response speed genuinely cannot be predicted, so expect CPU-speed replies.
Why each download is larger than the weights
Why each download is larger than the weights
These models are multimodal, so each one downloads a companion projector file automatically alongside the weights. The sizes above already include it.
Providers
Every provider is preconfigured. You pick it from a list and enter a key. The built-in local engine is pinned to the top, because it is the only option that needs no key at all.
Base URL is editable for
Custom, Local, and Azure OpenAI only. Everything else is fixed, so there is nothing to get wrong. For LM Studio, use http://localhost:1234/v1.
Apple Intelligence appears in the provider list for AI cleanup on Apple Silicon Macs, but not for the assistant. The on-device Foundation model does not back a streaming chat turn here, so it is filtered out of the assistant’s picker on purpose.
Keys and model names
Your API key lives in your operating system’s keychain, not a settings file. Each provider keeps its own key, so switching providers does not lose the one you already entered. The key is shared with AI cleanup, since both features use the same chat client. See Privacy. For the model, click Load models to fetch the provider’s list, or type any name directly. The picker accepts values that are not in the list.OpenRouter, Azure, and Perplexity quirks
OpenRouter, Azure, and Perplexity quirks
- OpenRouter. The only provider with built-in web search. It also sends
HTTP-RefererandX-Titlefor app attribution. - Azure OpenAI. The “model” is your deployment name. Whatever you paste from the portal is normalized to the v1 surface
https://{host}/openai/v1, so a bare resource URL or an AI Foundry project endpoint both work instead of returning 404 on a missing path. The key is sent as bothAuthorization: Bearerand theapi-keyheader, since gateways differ on which they honor. Requests use HTTP/1.1 and a smaller image budget, because Azure’s gateway truncates large bodies. - Perplexity. No model-list endpoint, so Load models does nothing. Type the model name.
Anthropic and the built-in engine
Anthropic and the built-in engine
- Anthropic. Authenticated with the native
x-api-keyheader plusanthropic-version, which works on both the OpenAI-compatible layer and the classic API. - Built-in local engine. Gemma-style chat templates reject a
systemrole, so the system prompt is folded into the first user message. Thinking is disabled in the template so a small model spends its tokens on the answer.
Local engine tuning
Two settings appear only for the built-in local engine. External providers, including Ollama and LM Studio, manage their own context and memory.How big a context window you want
How big a context window you want
The context window holds everything at once: the system instructions, your chat history, any screenshot (a single image can eat a big chunk), and the reply. Bigger holds more and keeps screen vision and web search reliable, but uses more memory.
16384 is a good step up if your machine has the RAM, and you can lower it later to save memory. The change applies when the engine starts.Why the model unloads after five minutes
Why the model unloads after five minutes
Unloading frees RAM and VRAM once the model has been idle that long, and it reloads automatically on next use. Five minutes keeps it warm through a working session without holding memory overnight.