3 docs tagged with "moe"

The last championship was not a speed test. Three real-world questions. No hints. Strict referee. One model finished. One crashed from context overflow. The findings are instructive.

The champion was crowned. The General reported clean passes, fast times, zero drift. The Emperor asked one question the arena was never designed to answer — and the champion timed out after 180 seconds of silence.

Ten models, two families, two drivers, one iGPU. The size sweep meant to map a smooth curve found a cliff instead — dense models fall off it, Mixture-of-Experts models do not. And the newer driver's gift turned out to have a price only dense models pay.