DEDUPEDWho it is forA home lab owner with a gaming PC and a Mac who wants both to serve models together.
The problemEach machine alone is too small for the model you want, and they cannot share work by default.
The outcomeOne private mesh where every node exposes the same /v1 API and requests route to the node that can serve them.
What you need first
- macOS, Linux or Windows (install script, PowerShell or Homebrew on Apple Silicon)
- One or more machines with a GPU or enough memory for the model
- curl and jq for the README's test requests
Steps
- On the first machine run
mesh-llm serve --model Qwen3-8B-Q4_K_M - Get the invite token and run the join command on each other machine
- Open the web console to see which node serves which model
- For a model too big for one box, use the split serving guide to run layer stages across machines
Prompt for your agent
Set up a private Mesh-LLM/mesh-llm mesh across <machine A> and <machine B>: start it with a Qwen3-8B model on the first, join the second by invite token, and confirm both appear in the console.
Caveat. This card is written from the Mesh-LLM/mesh-llm README, not from a test run by Deduped. Before you start, make sure you have macOS, Linux or Windows. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Mesh-LLM/mesh-llm and "Pool two home machines into a private model mesh"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer