Krea-2-Turbo · realrebelai

Krea-2-Turbo Q5_K_S

This file is exactly 8,871,171,296 bytes — 8.26 GiB / 8.87 GB at an effective 5.536 bits per weight. The nominal rate for Q5_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

8.26 GiB · 1 file

llama.cpp

llama-cli -hf realrebelai/KREA-2_GGUFs:Q5_K_S

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

Hugging Face CLI

hf download realrebelai/KREA-2_GGUFs BASE/Krea-2-Base-Q5_K_S.gguf

Direct download

BASE/Krea-2-Base-Q5_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

8.26 GiB

8.87 GB

Effective bpw

5.536

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata