Model preloading
When Default model preload is on, Loach sends an empty chat to the resolved default model at app launch — warming it into VRAM so the first real prompt of the session streams without the usual cold-start pause.
Enabling
Toggle Settings → General → Default model preload. It is off by default, and it is Ollama-only — hosted providers do not have a meaningful concept of warm vs cold from your side.
The trade-off
Preloading pins VRAM at launch even if you only opened Loach to re-read an old conversation. That is why it ships off: many users only want VRAM consumed when they are about to actually chat. Turn it on if you launch Loach with intent — you know the first thing you do is going to be a fresh prompt.
Which model gets warmed
Preload resolves through the same logic as Default model:
- If you pinned a specific model, that one.
- If you pinned to a provider, the most-recent model on that provider.
- Otherwise, your most recent (provider, model) pair — provided it is Ollama. If your most recent model is on an OpenAI-compatible endpoint, preload does nothing.