llamaperf

GLM-4.5-Air 106B (12B active)

on NVIDIA RTX 3090 · llama.cpp

Tone: positiveNVIDIA hardware
Aug 28, 2026
MTP (Multi-Token Prediction)
on
VRAM reported
24 GB

Use cases

creative-writingrp

Summary

User recommends enabling MTP in llama.cpp for GLM-4.5-Air, a 106B MoE with 12B active params, on 3090s. User notes MTP also works for full GLM-4.5. User mentions creative writing and RP finetunes and Intellect 3.x.