[whynotmaybe]

One Nvidia A100.

From the paper :

> We train using the AdamW [26] optimizer with a batch size of 5 and gradient accumulation over 20 steps on a single NVIDIA A100 GPU

So it's "consumer-grade" because it's available to anyone, not just businesses.

[spott]

That is the training gpu… the inference gpu can be much smaller.

[whynotmaybe]

I stand corrected.

Found on Yi-Zhe Song's Linkedin :

> Runs on a single NVIDIA 4090

https://www.linkedin.com/feed/update/urn:li:activity:7270141...

[ajdjspaj]

Thanks!