zai-org
GLM-5.1
text generationmit878.9K downloadsHugging Face
No server in stock right now has the 1685 GB this model needs for inference.
GPU memory it needs (estimate)
Rule of thumb from the model's size. Real needs depend on batch size, context length and framework.
Inference (full precision)
1685 GB
Inference (8-bit)
843 GB
Inference (4-bit)
421 GB
LoRA fine-tuning
1825 GB
QLoRA (8-bit base)
913 GB
Full fine-tuning
6740 GB