GUIDE 03Beginner20 pagesFree

OpenClaw + Ollama:
Run Your Agent for Free

Step-by-step setup to run OpenClaw entirely on local models. No API costs. Full privacy. Nothing leaves your machine. Works on most modern hardware with 16GB+ RAM.

Ollama InstallModel SelectionOpenClaw ConfigGPU AccelerationHybrid Setup$0 API Cost

Hardware Requirements

SetupRAMGPUBest ModelSpeed
Minimum16GBNot requiredqwen2.5:7bSlow but works
Recommended32GB8GB VRAMqwen2.5:32bGood
Optimal64GB+24GB VRAMqwen2.5:72bFast
VPS (cloud)32GB RAMN/Aqwen2.5:32bGood

Don't have the hardware? A 32GB RAM VPS from Hostinger runs ~$20/month — still cheaper than most API bills.

Not sure if your hardware can handle Ollama? Post your specs in the community and we'll tell you.

Get help from real practitioners doing this every day.

Join Free

Ollama is a tool that makes running large language models on your own hardware as simple as running a command. It handles downloading models, managing memory, and providing an API that OpenClaw can talk to.

Install on Linux (including your VPS):

bash
curl -fsSL https://ollama.ai/install.sh | sh

Verify the installation:

bash
ollama --version
# Should show: ollama version 0.x.x

Start the Ollama service:

bash
# Start as a background service
systemctl start ollama
systemctl enable ollama  # Start on boot

# Or run manually in a terminal
ollama serve

WHY THIS MATTERS

Ollama listens on port 11434 by default. This port should only be accessible locally — do not expose it to the internet. OpenClaw will connect to it via localhost.

Got Ollama running? Share your model and hardware setup in the community.

Get help from real practitioners doing this every day.

Join Free

Ollama Setup Checklist

Hardware meets minimum requirements (16GB RAM)
Ollama installed and running (ollama serve)
Model downloaded (qwen2.5:32b recommended)
Model tested with ollama run command
openclaw.json updated with Ollama baseURL and model
OpenClaw restarted and connected to Ollama
Test task completed successfully
GPU acceleration enabled (if applicable)
Hybrid routing configured (optional)
Ollama service set to start on boot

Download All Formats — Free

PDF guide, config templates, and checklist

Up Next

Guide 04: SOUL.md, AGENTS.md & HEARTBEAT.md Explained

Master the three config files that make your agent 10x more capable.

Read Guide 04
Ask the AI anything about OpenClaw →