OpenClaw + Qwen: Verified Setup Paths for OAuth and Ollama

The Quick Answer

OpenClaw officially supports Qwen OAuth through the qwen-portal provider and also works with local Qwen models through Ollama.

Watch: Qwen 3.6 + Ollama End-to-End Walkthrough

Running a local open-weights model (Qwen 3.6) through an agent runtime looks the same whether you’re pairing it with OpenClaw, Qwen Code, or any other Claude Code alternative. This 16-minute video walks through the full setup — installing Ollama, pulling the model, wiring the agent, and three real coding demos against Claude Code.

Apply the same Ollama wiring below for OpenClaw — the agent runtime is the only piece that differs.

Option 1: Use the Official Qwen OAuth Provider

# 1. Enable the Qwen auth plugin
openclaw plugins enable qwen-portal-auth

# 2. Restart the gateway
openclaw gateway restart

# 3. Start Qwen login and set it as default
openclaw models auth login --provider qwen-portal --set-default

# 4. Switch to the coder model explicitly
openclaw models set qwen-portal/coder-model

The flow uses Qwen’s device-code OAuth with a free-tier limit of 2,000 requests per day.

Option 2: Run a Local Qwen Model Through Ollama

# 1. Pull a Qwen model into Ollama
ollama pull qwen2.5-coder:32b

# 2. Let OpenClaw talk to Ollama
export OLLAMA_API_KEY="ollama-local"

# 3. Verify the model is visible
ollama list
openclaw models list

# 4. Set it as the default if needed
openclaw models set ollama/qwen2.5-coder:32b

The Most Important Ollama Caveat

Do not point OpenClaw at the OpenAI-compatible /v1 endpoint. The official Ollama page warns that native tool calling is the reliable path.

# Good: native Ollama API
http://ollama-host:11434

# Risky for tool calling
http://ollama-host:11434/v1

How to Verify Your Qwen Setup

openclaw models list
openclaw status
openclaw doctor
openclaw dashboard

If you are still setting up OpenClaw itself, start with How to Install OpenClaw. If Qwen is configured but replies are blank or tools fail, jump to the troubleshooting guide.