Rent a GPU

GLM-4.5-Air 106B-A12B hardware requirements

106B parameters (12B active, mixture of experts). Needs about 66.4 GB at Q4_K_M with 8K context.

Parameters106B12B active (MoE)
Q4_K_M · 8K66.4 GBthe usual download
FP16 · 8K214.1 GBfull precision
Runs well on4/51GPUs and Macs we track

Memory needed at each quantization

Weights, KV cache and runtime overhead, at 8K and 32K tokens of context.

QuantQuality8K context32K context
FP16Full quality214.1 GB218.8 GB
Q8_0Near-lossless114.8 GB119.4 GB
Q6_KExcellent89.1 GB93.7 GB
Q5_K_MVery good77.5 GB82.2 GB
Q4_K_MGood, most popular66.4 GB71 GB
Q3_K_MNoticeably degraded54 GB58.6 GB
Q2_KHeavily degraded41.9 GB46.5 GB

Model card

zai-org/GLM-4.5-Air on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run GLM-4.5-Air 106B-A12B on a rented GPU today.

It needs about 66.4 GB at Q4_K_M: a rented A100 / H100 80 GB runs it for about $1.11 to $3.99 an hour.

RunPodRent a GPU on RunPodVast.aiRent a GPU on Vast.ai

Every GPU and Mac checked

Sorted by memory. Bars show how much of each card GLM-4.5-Air 106B-A12B fills at the best quant that fits.

4 Runs well

NameMemory usedBest quantSpeed

3 Fits with heavy quantization

NameMemory usedBest quantSpeed

44 Too big

NameMemory usedBest quantSpeed

Other GLM models