FLUX.1-Krea-dev · calcuis

FLUX.1-Krea-dev IQ4_XS

This file is exactly 12,983,261,184 bytes — 12.09 GiB / 12.98 GB at an effective 8.727 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

12.09 GiB · 2 files
llama.cpp
llama-cli -hf calcuis/krea-gguf:IQ4_XS

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download calcuis/krea-gguf --include "flux1-krea-dev-iq4_xs.gguf"

This quantization is split across 2 files totalling 12.09 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
12.09 GiB
12.98 GB
Effective bpw
8.727
from real bytes ÷ params
Tensors
Header
GGUF metadata
FLUX.1-Krea-dev IQ4_XS — exact size and VRAM — ossmodeldb