Consulting from an ex-FAANG tech lead on private, self-hosted AI and software architecture: LLMs on your own hardware, on-device models for apps, private RAG, and system design reviews.https://tudalex.com/https://tudalex.com/blog/splash-vs-ollama-vs-mlx/https://tudalex.com/blog/splash-vs-ollama-vs-mlx/I benchmarked the new Splash inference engine against Ollama and Apple's mlx-lm with Qwen 3.8 27B, from an empty context to 200K tokens. Writing code gets 2–5× faster. Reading long prompts doesn't.Thu, 08 Oct 2026 00:00:00 GMThttps://tudalex.com/blog/bicameral/https://tudalex.com/blog/bicameral/An open-source tool that lets Claude Code hand mechanical work to an open model on your own machine. Free tokens, files that stay local, and Claude still checks the result.Wed, 07 Oct 2026 00:00:00 GMThttps://tudalex.com/blog/when-to-run-llms-locally/https://tudalex.com/blog/when-to-run-llms-locally/A practical checklist for deciding between a hosted API and self-hosted open-weight models — and the hidden costs on both sides.Wed, 07 Oct 2026 00:00:00 GMT