# Zhipu GLM-4.5-Air 106B (MoE) VRAM Requirements & Hardware Sizing Guide

> **Quick Summary (Answer Capsule)**: Running Zhipu GLM-4.5-Air 106B (MoE) requires 65.94 GB at Q4_K_M (4-bit), 119.34 GB at Q8_0 (8-bit), and 219.58 GB at FP16. Recommended hardware sweet spot: AMD Ryzen AI Max+ 395 Strix Halo 128GB. Scaling context past 32k tokens requires enabling FP8 KV-cache (-ctk q8_0) to prevent CUDA allocation failures.

## Memory Specifications by Precision
| Quantization Format | Precision Level | Required VRAM (8k context) | Quality Retention | Minimum Recommended GPU |
|---|---|---|---|---|
| 4-Bit (Q4_K_M) | Recommended Default | 65.94 GB | >98.2% Perplexity | AMD Ryzen AI Max+ 395 Strix Halo 128GB |
| 8-Bit (Q8_0) | Near Lossless | 119.34 GB | ~99.9% Perplexity | Workstation / High-Tier GPU |
| 16-Bit (FP16/BF16) | Uncompressed Full | 219.58 GB | 100% Fidelity | Multi-GPU / Datacenter |

## Architectural Memory Analysis
GLM 4.5 Air 106B is a high-efficiency Mixture-of-Experts model containing 106B total parameters with 14.5B active parameters per token across 48 layers with 8 GQA key-value heads. Requiring ~64 GB at 4-bit precision, it is designed for dual RTX 5090 (64GB) rigs, AMD Strix Halo 128GB, and workstation-scale AI deployments.

## Tier 1 Free Software Optimization ($0)
On Dual RTX 5090 or Mac Studio workstations, pass `-fa on -ctk q8_0` in llama.cpp to preserve context buffer space. This enables 32k multi-lingual context analysis within 68 GB total system VRAM.

## 1-Click Launch Terminal Snippets
- Ollama: `ollama run glm-4-5-air-106b:q4_K_M`
- vLLM: `vllm serve Z.ai / Zhipu/glm-4-5-air-106b --max-model-len 8192 --gpu-memory-utilization 0.95`

## Verified Hardware & Cloud Pathways
- Amazon Hardware: [Ryzen AI Max+ 395 128GB mini PC](https://www.amazon.com/s?k=Ryzen+AI+Max%2B+395+128GB+mini+PC&tag=sparecables-20) (rel="noopener sponsored")
- RunPod Cloud Rental: [Deploy Instance](https://runpod.io?ref=ynypzu94) (rel="noopener sponsored")
- Vast.ai Cloud Rental: [Deploy Instance](https://cloud.vast.ai/?ref_id=723130) (rel="noopener sponsored")

---
*Interactive Sizing Calculator available at: https://www.gpugarden.com/vram/glm-4-5-air-106b/*