No Cloud, No API Keys: Local Open-Source Coding with Trinity Mini, OpenCode, and MLX

No API keys. No cloud. No per-token cost. Just your Mac. In this video, I show you how to run Arcee AI's Trinity Mini (26B parameters, 3B active) locally on Apple Silicon using MLX, and wire it up to OpenCode as a fully local AI coding assistant. Everything runs on-device — ideal for air-gapped environments, regulated industries, or anyone who wants a private coding AI. I cover the full setup: choosing the right quantization for your hardware, benchmarking generation speed across all quantizations, and configuring OpenCode to talk to the local model. I also check Trinity's results with Claude Code! ⭐️⭐️⭐️ More content on Substack at https://www.airealist.ai ⭐️⭐️⭐️ *** MODELS Arcee Trinity Mini (base) → https://huggingface.co/arcee-ai/Trinity-Mini Trinity Mini MLX 8-bit → https://huggingface.co/mlx-community/Trinity-Mini-8bit Trinity Mini MLX 6-bit → https://huggingface.co/mlx-community/Trinity-Mini-6bit Trinity Mini MLX 4-bit → https://huggingface.co/mlx-community/Trinity-Mini-4bit Trinity Mini on OpenRouter (free) → https://openrouter.ai/arcee-ai/trinity-mini:free *** CODE Full walkthrough + scripts → https://github.com/juliensimon/arcee-demos/tree/main/trinity-mini-mlx *** TOOLS MLX by Apple → https://github.com/ml-explore/mlx mlx-lm (model serving) → https://github.com/ml-explore/mlx-lm OpenCode (terminal coding assistant) → https://opencode.ai Arcee AI → https://www.arcee.ai