Ethereum co-founder Vitalik Buterin argued on Sept. 17 that local AI is approaching a practical turning point, saying Qwen 3.8 Flash and recent improvements in llama.cpp had brought local models close to handling a "large share" of tasks on his Strix Halo laptop. He described a setup where a local model coordinates requests to stronger remote systems while withholding the user's full personal context, so a remote service receives only the question or context the local model selects. A benchmark image attached to the post showed 10 workloads, with reported input-processing rates ranging from 109.82 to 373.22 tokens per second and output generation ranging from 18.42 to 33.37 tokens per second. Buterin said wallet software still needs a much higher bar before it can hand an AI control over crypto assets, and that local inference can improve privacy while the power to move funds remains behind separate, enforceable controls. In an April account, he described a narrower role for laptop models, writing that Qwen3.5:35B could handle bounded tasks and familiar programming work, while advanced independent agents remained beyond laptops' practical reach. Qwen3.8-Flash-Next, released by Alibaba's Qwen team, is an open-weight multimodal mixture-of-experts model with 125 billion parameters, plus another 51 billion in n-gram embedding tables, while 6 billion parameters are activated per token.