GLM-5.3 320B (18B active) Flash
on Unknown GPU
Use cases
coding
Summary
User reports GLM 5.3 Flash at 30 t/s decode and 1200 t/s prefill, compared with Qwen Flash Next at 125 t/s decode and 3000 t/s prefill.
No hardware or engine details are given.
User says GLM 5.3 Flash is slower but better at thinking, and that it produced the same front-end issues and bugs as Qwen Flash Next and a 27B model on a coding task.