New conversation · Llama 3.1 8B Private
offlinesandboxsigned
Private AI Chat
Start the local server to run inference on your machine.
Mock responses are active until then.
// terminal · $
$ pip install ltce $ ltce pull lattice/llama-3.1-8b-private $ ltce serve --port 8080 --sandbox → Lattice Inference Server running → http://localhost:8080
ctx 0 / 8k · ε spent 0.00
/clear · /export · /verify · /eps
no keys leave the box