llamaperf

GLM-5.3

on M3 Ultra · Open WebUI

Tone: mixed
Nov 20, 2026
Throughput
12-15 t/s gen
Quant
4-bit dynamic

Use cases

long-context

Summary

User compares GLM-5.3 on an M3 Ultra against ChatGPT's browser harness on a research prompt about democracy and labor power. GLM-5.3 ran through Open WebUI at a 4-bit dynamic quant and took about 27 minutes to answer, against about 7 minutes for ChatGPT. User puts GLM-5.3 at roughly 12-15 t/s and Astra at a reported 40 t/s, and rates Astra's historical examples better while GLM found better high-level theoretical sources.