Z-Image · unsloth

Z-Image Q6_K

This file is exactly 6,101,921,856 bytes — 5.68 GiB / 6.10 GB at an effective 7.931 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

5.68 GiB · 1 file

llama.cpp

llama-cli -hf unsloth/Z-Image-GGUF:Q6_K

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

Hugging Face CLI

hf download unsloth/Z-Image-GGUF z-image-Q6_K.gguf

Direct download

z-image-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

5.68 GiB

6.10 GB

Effective bpw

7.931

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata