Krea-2-Turbo · wikeeyang
Krea-2-Turbo MXFP4
This file is exactly 7,884,205,984 bytes — 7.34 GiB / 7.88 GB at an effective 4.920 bits per weight. The nominal rate for MXFP4 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
7.34 GiB · 1 file
llama.cpp
llama-cli -hf wikeeyang/Krea2-Turbo-HD-V1:MXFP4
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download wikeeyang/Krea2-Turbo-HD-V1 Krea2-Turbo-HD-V1-MXFP4.gguf
Direct download
Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.
Size
7.34 GiB
7.88 GB
Effective bpw
4.920
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata