dense
A model where every parameter runs for every token, with no routing. A 27B dense model does 27B parameters of work on each token it generates. Simpler than MoE, but slower at the same total size, because there is no way to skip most of the weights.
In a listing, dense is what you infer from an absence. qwen3.6-35b-a3b names
its active parameters; qwen3.6-27b has no a-number, so all 27 billion run
every time.