This quickstart covers:

  1. Downloading & running an LLM on your machine
  2. Downloading & intializing the node client
  3. CLI commands to use the client

​
Prerequisites

​
Run the GPU node (CLI)

1

Sign up

  1. Create an account here
  2. Create an API key on the dashboard
  3. Create a node on the dashboard
2

Create a virtual environment

For example, using venv

python3 -m venv venv
source venv/bin/activate
3

Install galadriel

pip install galadriel-node
4

Setup the environment

Make sure to set the correct API key and node-id that you created on the dashboard.

Other values should be the default ones.

galadriel init
5

Run the node

galadriel node run

Or run the node in a background process

nohup galadriel node run > logs.log 2>&1 &
# To shut it down
pgrep -af python
kill <PID>

If this is your first time running the GPU node, it will perform hardware validation and LLM benchmarking, to ensure your setup is working correctly and is fast enough.

6

Check node status

In another terminal tab:

galadriel node status

If the status is online you’ve successfully started your GPU node and it’s serving LLM inference requests to the network.

​
Checking node stats

Available if the GPU node is initialized and its status is online.

galadriel node stats

​
Checking network stats

Available if the GPU node is initialized and its status is online.

galadriel network stats

​
What’s next?

  • Get rewards for running the node and serving LLM inference to the network.
  • Check out how to update the galadriel-node.