llamaperf

Muse 30B Glimmer

on M4 Max 128GB · WebGPU

Apple hardware
Sep 7, 2026
Throughput
25.0 t/s gen
Quant
UD-Q2_K_XL (GGUF)
System RAM
128 GB

Summary

User reports running a model in-browser with custom WebGPU kernels, at speed comparable to llama.cpp.