AI Why My Mac Mini M4 Outperforms Dual RTX 3090s for LLM Inference I built a dual RTX 3090 server for local LLM inference. A Mac Mini M4 turned out to be 27% faster and 22× more efficient. Here's why memory bandwidth beats raw GPU power. Stephane Thirion 16 Feb 2026 · 2 min read
AI NVIDIA GTC Paris 2025: Europe’s AI Launchpad GTC Paris 2025 highlighted NVIDIA's end-to-end AI stack: Blackwell GPU deployment, AI-Q Blueprint agents, and sovereign infrastructure scaling across Europe. As enterprise adoption grows, open-source frameworks like LangChain and AutoGen offer modular, hardware-agnostic alternatives. Stephane Thirion 11 Jun 2025 · 4 min read
ComfyUI Self-hosted ComfyUI install - Ubuntu 24.02 How to Install ComfyUI on Ubuntu 24.04 in /opt/ComfyUI with GPU Support and Auto-Start Stephane Thirion 6 Jun 2025 · 3 min read
Homelab Homelab serie -- The software 3/3 SamanthAI my artificial intelligence learning lab, all about LLMs and personnal assistant Stephane Thirion 24 Mar 2025 · 3 min read
Homelab Homelab serie -- The hardware For as long as I can remember, I've had a homelab. Honestly, it’s been so many years now that I can hardly recall exactly when or how it all began Stephane Thirion 15 Mar 2025 · 7 min read
Ollama Setting Up Ollama with Open-WebUI: A Docker Compose Guide In this blog post, we'll dive into setting up a powerful AI development environment using Docker Compose. The setup includes running the Ollama language model server and its corresponding web interface, Open-WebUI, both containerized for ease of use. Stephane Thirion 24 Jan 2025 · 4 min read
AMD E2Evc Lisboa November 2019 One more time this event have been full of good stuff and I learned a lot going from a presentation to another and speaking with everyone. I noted few products Stephane Thirion 13 Nov 2019 · 2 min read
AI
