Ethereum's Buterin runs AI agent locally with open-source Qwen model, Signal messaging

Per the article in Decrypt by Stacy Jones: "Buterin runs the open-source Qwen3.5:35B model locally via llama-server. And after testing multiple setups, he prefers using a laptop with an Nvidia 5090 GPU that hits 90 tokens per second. That's fast enough to feel usable, Buterin added."