What Actually Runs on Your Machine
“The open models have caught up” is true — and misleading. The best open model trails the world’s best by only 3 points, but it has 2.8 trillion parameters and runs only in the data centre. What fits on your graphics card lags by around 23 points. “Open” is not “local” — and a computed-down model doesn’t hiss, it lies with confidence. Running it costs more than the card.
Read more →