Running Opencode with Ollama on mac.
Summary
The article provides a practical guide to running local LLMs on macOS using Ollama, OpenCode, and Docker Sandboxes (sbx). It covers selecting models (Qwen 3.8 and Gemma4), installing tools, creating sandbox kits, and configuring OpenCode to run with Ollama on the host, including memory considerations and a run command. This is a hands-on workflow valuable for AI tool developers and SMB IT teams exploring local AI development environments.