Comment by labcomputer

Right. Couple things to note though:

- Larger MoE models only need compute proportional to the number of active parameter, so Qwen3.8-Flash-Next (180b with 6b active) runs more tok/sec than Qwen3.8-27b on the same hardware.

- Larger models typically have higher quality output and require fewer thinking tokens to get to an answer.

Consequently, measuring time to complete a task with a wall clock, the speed difference is less than you would expect.