Quickstart
From nothing to a chat and a picture on one machine. Everything runs on your own hardware.
1. Install
curl -fsSL https://dl.inclavate.io/install.sh | shirm https://dl.inclavate.io/install.ps1 | iexOpen a new terminal, then check it worked with dppan --version. Other ways to install, and what the installer changes: Installation.
2. Start the orchestrator
The orchestrator takes every request and sends the work to the machines that do it. In one terminal:
dppan-orchestrator --port 8001 --admin-token mysecret--admin-token turns on the dashboard's Admin tab; use your own value.
What a launch looks like
Each process greets you with the Inclavate banner — version, platform, where it's listening, and quick links. Starting dppan-orchestrator --port 8001:
◆ ██╗███╗ ██╗ ██████╗██╗ █████╗ ██╗ ██╗ █████╗ ████████╗███████╗
╱ ╲ ██║████╗ ██║██╔════╝██║ ██╔══██╗██║ ██║██╔══██╗╚══██╔══╝██╔════╝
◆ ◆ ██║██╔██╗ ██║██║ ██║ ███████║██║ ██║███████║ ██║ █████╗
╲ ╱ ██║██║╚██╗██║██║ ██║ ██╔══██║╚██╗ ██╔╝██╔══██║ ██║ ██╔══╝
◆ ██║██║ ╚████║╚██████╗███████╗██║ ██║ ╚████╔╝ ██║ ██║ ██║ ███████╗
╚═╝╚═╝ ╚═══╝ ╚═════╝╚══════╝╚═╝ ╚═╝ ╚═══╝ ╚═╝ ╚═╝ ╚═╝ ╚══════╝
Run AI privately, across your own devices · Distributed LLM Inference
orchestrator · routes inference across nodes
version 0.8.5
platform macos-arm64
system 8 cores
listen 0.0.0.0:8001
gateway 0.0.0.0:9001
mode local
database none
Docs docs.inclavate.io · Site inclavate.io · Feedback [email protected] · Follow @inclavateai
© 2026 Inclavate · Free to run · Proprietary
Legal inclavate.io/privacy · /terms · /acceptable-use · /data-retentionThe banner shows only in an interactive terminal — piped output, daemons (systemd/Docker), and CI stay clean. Turn it off anywhere with --no-banner or INCLAVATE_NO_BANNER=1.
3. Add a chat model
A node runs the model. In a second terminal, download a small one and join it to the orchestrator:
dppan pull llama3.2:1b
dppan join --orchestrator http://localhost:8001 --model llama3.2:1b \
--gguf ~/.dppan/models/llama3.2-1b-full.gguf4. Chat
curl -X POST http://localhost:8001/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"llama3.2:1b","messages":[{"role":"user","content":"Hello!"}],"max_tokens":200}'Or start the dashboard in a third terminal and open http://localhost:3000:
dppan ui --orchestrator http://localhost:8001 --port 3000

5. Make an image
Install an image model (about 6.5 GB), then restart the orchestrator: it serves the models installed when it starts.
dppan pull --visual z-image-turboStop the orchestrator with Ctrl-C and start it again with the command from step 2. Then ask for a picture:
curl -X POST http://localhost:8001/v1/generations \
-H 'Content-Type: application/json' \
-d '{"model":"z-image-turbo","modality":"image","seed":42,
"params":{"prompt":"a paper crane on a windowsill, morning light"}}'The answer is a job. Poll GET /v1/generations/<id> until its state is completed, then download output_artifacts[0] from /v1/artifacts/<artifact id>: a PNG. In the dashboard, the same is on Generate › Image.
Next
- More machines: Multi-machine setup, and Sharded download for models bigger than one machine.
- More to make: Chat, Speech and voice, Music, Images and Video.
- How it fits together: How Inclavate works.
- Look things up: CLI, Configuration and the REST API.