beipo-ai
NorthCUA-Pro
image text to textapache-2.0811 downloadsHugging Face
No server in stock right now has the 887 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)
887 GB
Inference (8-bit)
443 GB
Inference (4-bit)
222 GB
LoRA fine-tuning
961 GB
QLoRA (8-bit base)
480 GB
Full fine-tuning
3548 GB