Menu

The model page said 8-bit. The checkpoint is 4.49 bits per parameter.
πŸ“°

The model page said 8-bit. The checkpoint is 4.49 bits per parameter.

DEV Community: pythonΒ·pm25coderΒ·11 days ago
#FISlzdZH
#devtopython#devto#dev#weights#bits
Reading 0:00
15s threshold

I was working out how much disk Kimi K3.1 Pro would need, and the model page gave me two numbers that cannot both be true. The card says MXFP4 weights / MXFP8 activations . The badge beside the download button says 8-bit precision . So I added up the shards I would actually pull and divided by the parameter count the platform reports, and got 4.49 bits per parameter.

That is not a rounding difference. 2.78 trillion parameters at 8 bits is 2,780 GB; at 4 bits it is 1,390 GB. The 96 shards in that repository come to 1,561 GB. So one of those three numbers is answering a question I did not ask, and if you are sizing a download or a disk you need to know which one it is.

The check is fifteen lines and it runs against the public API:

import json , urllib . request

REPO = " moonshotai/Kimi-K3.1-Pro "

api = json . load ( urllib . request . urlopen ( f " https://huggingface.co/api/models/ { REPO } ?blobs=true " ))

files = [ f for f in api [ " siblings " ] if f . get ( " size " ) and f [ " rfilename " ].…

Continue reading β€” create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.