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/Trini...
Trinity Mini MLX 8-bit → https://huggingface.co/mlx-community/...
Trinity Mini MLX 6-bit → https://huggingface.co/mlx-community/...
Trinity Mini MLX 4-bit → https://huggingface.co/mlx-community/...
Trinity Mini on OpenRouter (free) → https://openrouter.ai/arcee-ai/trinit...
*** CODE
Full walkthrough + scripts → https://github.com/juliensimon/arcee-...
*** 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
On this page of the site you can watch the video online No Cloud, No API Keys: Local Open-Source Coding with Trinity Mini, OpenCode, and MLX with a duration of hours minute second in good quality, which was uploaded by the user Julien Simon 15 March 2026, share the link with friends and acquaintances, this video has already been watched 20,024 times on youtube and it was liked by 42 viewers. Enjoy your viewing!
