Local LLM
Your models. Your workspace.
A private place to use a model that runs on your own computer. Chat, see which models you have, check which ones can look at pictures, and time how fast they answer. It works with Ollama, LM Studio, llama.cpp, and other apps that speak the same local API.
This computer
Chats, pictures, and speed tests stay in a data folder on this machine. There is no account, and nothing is sent back.
The app you started
Studio does not install or start Ollama, LM Studio, or llama.cpp. Point it at the address that app is already using.
Pictures, when it can see
Models that can look at pictures are marked. If a model cannot, the button to attach a picture stays hidden.
Speed on your machine
It times one model at a time: how long the first words take, and how fast the rest of the reply comes in. That is speed on your computer, not a score for the answer.
A public cloud address is refused. An address on another computer on your network is saved only after you confirm, because your messages then leave this machine.