Topic
Large language models.
Across 155 small-model experiments centered on Qwen 3.5 4B, the same thing kept working: give the model something executable it can check against the evidence it has, and it punches far above its benchmark weight. Here is the field guide — the levers that worked, how I know they're real, and the frontier they opened up.
The headline benchmark is the least durable thing in a model release. Here is how to read access, licenses, cards, eval protocols, and serving facts before you commit engineering to a number you cannot reproduce.
vLLM treats the KV cache like OS virtual memory — non-contiguous paged blocks — and schedules work at the token, not the request. You get high aggregate throughput; the cost is that per-request latency becomes something you tune rather than something you get for free.