llamaperf

GLM-5.3 320B (18B active) Flash

on Unknown GPU · Project Maya

Tone: positive
Oct 12, 2026
Throughput
30.0 t/s gen

Summary

User reports GLM-5.3 Flash at 30 tok/s with Project Maya, up from about 10 tok/s previously. Setup is Project Maya, an engine built for this model, with experts kept on GPU, RAM and NVMe SSD. The user finds GLM-5.3 Flash more enjoyable than Qwen 3.8 Flash-Next so far and is still testing.