Z-Image-Turbo · unsloth

Z-Image-Turbo Q4_K_S

This file is exactly 4,710,950,976 bytes — 4.39 GiB / 4.71 GB at an effective 6.123 bits per weight. The nominal rate for Q4_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

4.39 GiB · 1 file

llama.cpp

llama-cli -hf unsloth/Z-Image-Turbo-GGUF:Q4_K_S

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

Hugging Face CLI

hf download unsloth/Z-Image-Turbo-GGUF z-image-turbo-Q4_K_S.gguf

Direct download

z-image-turbo-Q4_K_S.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

4.39 GiB

4.71 GB

Effective bpw

6.123

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata