
Thinking of building an AI data center to sell compute? Power, money, and Taiwan's grid limits
AI compute is hot, and a lot of owners are asking whether they should build their own data center and sell tokens. This post covers how a to…
Every article tagged “地端AI”, newest first.
10 articles
AI compute is hot, and a lot of owners are asking whether they should build their own data center and sell tokens. This post covers how a to…

Mac Studio goes up to 512 GB of unified memory. It fits large models that most GPUs can't hold, and it stays quiet and uses little power. Bu…

Many owners assume that getting AI to understand their company means training their own model. When knowledge changes and answers need sourc…

Cloud models are smarter and need no hardware. Open-source models run inside your company, and your data stays put. This post compares prici…

On-premise AI keeps your data inside the company. It is not a cure-all. This post lists seven limits honestly: it is not as smart as top clo…

On the same GPU, one user can get over a hundred characters per second. With thirty people asking at once, the first character can take a mi…

On-prem AI hardware ranges from a workstation around NT$100,000 to servers costing over NT$10 million. This post splits GPUs into five tiers…

There are more than twenty open-source model families, and the leaderboards change every day. As the owner, you are not picking the stronges…

The most expensive part of fine-tuning an AI model isn't the hardware. It's trial and error in the wrong direction. At a GTC Taipei 2026 wor…

At GTC Taipei 2026, NVIDIA's LLM customization workshop walked through one complete case: an 8-billion-parameter open-source model went from…