FLUX.1-Krea-dev · QuantStack

FLUX.1-Krea-dev Q6_K

This file is exactly 9,848,349,984 bytes — 9.17 GiB / 9.85 GB at an effective 6.620 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

9.17 GiB · 1 file

llama.cpp

llama-cli -hf QuantStack/FLUX.1-Krea-dev-GGUF:Q6_K

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

Hugging Face CLI

hf download QuantStack/FLUX.1-Krea-dev-GGUF flux1-krea-dev-Q6_K.gguf

Direct download

flux1-krea-dev-Q6_K.gguf

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.

Repository →

Size

9.17 GiB

9.85 GB

Effective bpw

6.620

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata