● Covered by 1 source · 1 reportLow impact1 neutral
Guide to Setting Up OpenCode with Ollama and sbx on Mac for Local LLM Development
Key points
- Uses Ollama for local LLM execution on Apple Silicon.
- Integrates OpenCode as a development harness.
- Employs Docker sandboxes (sbx) for isolated environments.
- Provides steps for installing tools and configuring models.
Local LLM Development Environment
The article outlines a method for setting up a local development environment for large language models (LLMs) on Apple Silicon Macs. This configuration uses OpenCode as a development harness, Ollama for running LLMs, and Docker sandboxes (sbx) for isolation. The setup is presented as suitable for building web applications with local LLMs.
Tool Selection and Rationale
Ollama is chosen for its ease of use, performance on Apple Silicon via MLX, and stable operation. OpenCode is selected as the development harness. Docker sandboxes (sbx) are used to containerize local models, providing isolation similar to how frontier models are handled in professional settings.
Installation Steps
Installation instructions are provided for Docker Sandbox (sbx) and OpenCode via Homebrew. Ollama requires a direct download and installation from its website. The guide specifies pulling two models: Qwen 3.8 27B mxfp8 (32GB) and Gemma 4 31b mxfp8 (34GB) using Ollama's command-line interface. Alternative models are suggested for Macs with less than 48GB RAM.
Project Configuration
Project configuration involves setting up an sbx kit for each project. This includes creating a `spec.yaml` file and an `opencode-local.json` file within a `./sbx-kit/` directory. The `spec.yaml` configures the sandbox to allow network access to localhost ports used by Ollama and OpenCode, and sets environment variables. The `opencode-local.json` specifies the default model to be used.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Reporting from
A guide details how to configure OpenCode, Ollama, and Docker sandboxes (sbx) on Apple Silicon Macs for local large language model (LLM) development. This setup allows developers to run models like Qwen 3.8 and Gemma 4 locally for web application development.