For me Qwen3.8-Flash-Next beats both GLM5.3-Flash and the older DeepSeek v4.1 Flash 0731.

It uses all if my 6 rtx3090s but runs 7 sessions at combined 200tok/s and prefill of 7k on a cheap pc (no threadripper, all gpus via usb4).

DeepSeek v4.1 Flash 1017 is better but it is also 3x the size... And I find running quant below 3.8bits unusable.