CAUTION
Before proceeding, review the security risks in the Overview tab. OpenClaw is an AI agent that can access your files, execute commands, and connect to external services. Data exposure and malicious code execution are real risks. Strongly recommended: Run OpenClaw on an isolated system or VM, use dedicated accounts (not your main accounts), and never expose the dashboard to the public internet without authentication.
On your DGX Spark, open a terminal and run the official install script. This installs OpenClaw and its dependencies on your Linux system.
curl -fsSL https://openclaw.ai/install.sh | bash
After dependencies are downloaded, OpenClaw will show a security warning. Read the risks; if you accept them, use the arrow keys to select Yes and press Enter.
Work through the prompts as follows.
Quickstart vs Manual: Choose Quickstart.
Model provider: To use a local model (recommended for DGX Spark), go to the bottom of the list and select Skip for now—you’ll configure the model later. To use a cloud model instead, pick a provider and follow its instructions.
Filtering models by provider: Select All Providers. On the next prompt for the default model, choose Keep Current.
Communication channel: You can connect a channel (e.g., messaging) to use the bot when away from the machine, or select Skip for Now and configure it later.
Skills: We recommend selecting No for now. You can add skills later from the web UI or Clawhub after you’ve tested the basics.
Homebrew: If you are prompted to install Homebrew, select No—Homebrew is for macOS only and is not needed on Linux.
Hooks: We recommend selecting all three for a better experience. Note that this may log data locally; enable only if you’re comfortable with that.
Dashboard URL: The terminal will print a URL for the OpenClaw dashboard. Save this URL (and any access token shown)—you’ll need it to open the web UI.
Finish: Select Yes on the final prompt to complete installation.
You can now open the OpenClaw dashboard in a browser using the URL and token from the installer.
OpenClaw will connect to a local, OpenAI-compatible endpoint served by vLLM. This playbook uses the agent-ready nvidia/Qwen3.6-35B-A3B-NVFP4 recipe — the same one documented in the vLLM playbook's Run Agent Ready Qwen3.6 35B Model with vLLM tab. The NVFP4 quantization and speculative decoding give strong tool-calling and reasoning quality while leaving headroom on DGX Spark's 128GB unified memory.
In a separate terminal on your DGX Spark, follow the vLLM playbook's Run Agent Ready Qwen3.6 35B Model with vLLM tab to launch the server. Run it on its own terminal so the gateway and the model server can run side by side. That tab serves nvidia/Qwen3.6-35B-A3B-NVFP4 on an OpenAI-compatible API at http://localhost:8000/v1.
Once the server reports Application startup complete, verify it from another terminal before continuing:
curl http://localhost:8000/v1/models
You should see nvidia/Qwen3.6-35B-A3B-NVFP4 in the returned list.
Open the OpenClaw config file in your preferred editor (e.g. nano, vim, or a graphical editor). The config path is:
~/.openclaw/openclaw.json
Example with nano:
nano ~/.openclaw/openclaw.json
Add or update the models section so it includes the vLLM provider pointing at the endpoint from Step 3. vLLM does not require an API key, so any non-empty placeholder works:
"models": {
"mode": "merge",
"providers": {
"vllm": {
"baseUrl": "http://localhost:8000/v1",
"apiKey": "vllm",
"api": "openai-responses",
"models": [
{
"id": "nvidia/Qwen3.6-35B-A3B-NVFP4",
"name": "nvidia/Qwen3.6-35B-A3B-NVFP4",
"reasoning": true,
"input": ["text"],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 8192
}
]
}
}
}
The id and name must match the model handle served by vLLM (nvidia/Qwen3.6-35B-A3B-NVFP4). contextWindow matches the --max-model-len from Step 3.
NOTE
If OpenClaw reports an unsupported-endpoint error against the Responses API, change "api": "openai-responses" to the OpenAI chat-completions variant for your OpenClaw version — vLLM always exposes /v1/chat/completions.
~/.openclaw/openclaw.json and picks up the new provider.You can also ask OpenClaw which model it’s using. In the gateway chat UI you can switch models by typing: /model MODEL_NAME (e.g. /model nvidia/Qwen3.6-35B-A3B-NVFP4).
Skills add capabilities but also risk; only enable skills you trust (e.g., community-vetted ones). To add a skill:
For more usage and configuration details, see the OpenClaw documentation.