[Vitalik: The Intersection of Ethereum Infrastructure and AI Continues to Expand, Models Need Optimization for Relevant Use Cases] Vitalik Buterin shared the latest progress on his self-hosted large language model (LLM) setup, noting that the intersection of Ethereum infrastructure and AI is continuously expanding. He mentioned that Deepseek V4 has been released, with its 2-bit quantized version capable of running within 90GB of memory, achieving a speed of approximately 35 tokens/second on Apple hardware but only about 7 tokens/second on AMD. He emphasized that true support for multiple hardware vendors is key to distinguishing 'decentralized AI' from 'CROPS AI.' Additionally, Mistral's Leanstral model (focused on Lean code writing) can run within 70GB and delivers performance comparable to large models with 1T parameters.