siamcafe/bomllm
Self-hosted Thai AI infrastructure — Mac Mini M4 Pro running TURBO-Fable 27B at 18.5 tok/s for $0.54/day. Fleet of 9 machines, GOD CONFIG v7.0, 40 IRON safety rules. Production-grade Open WebUI + LiteLLM + Ollama MLX stack.
GitHub repository with 43 stars and 8 forks.
Language: Python
Topics: litellm, mac-mini, mlx, ollama, comfyui, fleet-management, flux, local-inference, open-webui, production-ai