Rent a GPU

GLM-5 744B-A40B hardware requirements

744B parameters (40B active, mixture of experts). Needs about 452.4 GB at Q4_K_M with 8K context.

Parameters744B40B active (MoE)
Q4_K_M · 8K452.4 GBthe usual download
FP16 · 8K1489.3 GBfull precision
Runs well on0/51GPUs 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 quality1489.3 GB1491.5 GB
Q8_0Near-lossless791.8 GB794 GB
Q6_KExcellent611.4 GB613.6 GB
Q5_K_MVery good530.5 GB532.7 GB
Q4_K_MGood, most popular452.4 GB454.6 GB
Q3_K_MNoticeably degraded365 GB367.2 GB
Q2_KHeavily degraded280.3 GB282.5 GB

Model card

zai-org/GLM-5 on Hugging Face: licence, prompt format and GGUF builds.

Run it in the cloud

Run GLM-5 744B-A40B on a rented GPU today.

It needs about 452.4 GB at Q4_K_M: a rented 8× A100 / H100 runs it for about $8.88 to $31.92 an hour. Compare with Claude and APIs or see how it scores against them.

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-5 744B-A40B fills at the best quant that fits.

51 Too big

NameMemory usedBest quantSpeed

Other GLM models