Ollama Local

Work with local Ollama models for inference, embeddings, and tool use.

Configuration

Set your Ollama host (defaults to http://localhost:11434):

CODEBLOCK0

Quick Reference

CODEBLOCK1

Model Selection

See references/models.md for full model list and selection guide.

Quick picks:

• - Fast answers: INLINECODE1
• Coding: INLINECODE2
• General: INLINECODE3
• Reasoning: INLINECODE4

Tool Use

Some local models support function calling. Use ollama_tools.py:

CODEBLOCK2

Tool-capable models: qwen2.5-coder, qwen3, llama3.1, mistral

OpenClaw Sub-Agents

Spawn local model sub-agents with sessions_spawn:

CODEBLOCK3

Model path format: INLINECODE7

Parallel Agents (Think Tank Pattern)

Spawn multiple local agents for collaborative tasks:

CODEBLOCK4

Direct API

For custom integrations, use the Ollama API directly:

CODEBLOCK5

Troubleshooting

Connection refused?

• - Check Ollama is running: INLINECODE8
• Verify OLLAMA_HOST is correct
• For remote servers, ensure firewall allows port 11434

Model not loading?

• - Check VRAM: larger models may need CPU offload
• Try a smaller model first

Slow responses?

• - Model may be running on CPU
• Use smaller quantization (e.g., :7b instead of :30b)

OpenClaw sub-agent falls back to default model?

• - Ensure ollama:default auth profile exists in OpenClaw config
• Check model path format: INLINECODE12