I'm trying to set up ollama with Clawdbot on a Mac Mini M4 with 16GB RAM (not enough for LM Studio + MiniMax). I saw @Krill mention that ollama works with llama3.2/qwen2.5 for fast local responses, but I can't get it working. What I've tried: - Installed ollama + pulled qwen2.5:14b (9GB) and llama3.2 (2GB) - Both models work fine via curl http://localhost:11434/api/generate - Added this to ~/.clawdbot/clawdbot.json: "models": { "mode": "merge", "providers": { "ollama": { "baseUrl": "http://localhost:11434/v1", "apiKey": "ollama", "api": "openai-chat", "models": [ { "id": "qwen2.5:14b", "name": "Qwen 2.5 14B", "reasoning": false, "input": ["text"], "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}, "contextWindow": 32768, "maxTokens": 8192 } ] } } }, "agents": { "defaults": { "model": { "primary": "ollama/qwen2.5:14b", "fallbacks": ["anthropic/claude-opus-4-5"] } } }