Krea-2-Turbo · realrebelai

Krea-2-Turbo Q8_0

This file is exactly 13,625,717,856 bytes — 12.69 GiB / 13.63 GB at an effective 8.503 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 430 tensors parsed

Get it

12.69 GiB · 1 file
llama.cpp
llama-cli -hf realrebelai/KREA-2_GGUFs:Q8_0

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

Hugging Face CLI
hf download realrebelai/KREA-2_GGUFs TURBO/Krea-2-Turbo-Q8_0.gguf
Direct download

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
12.69 GiB
13.63 GB
Effective bpw
8.503
from real bytes ÷ params
Tensors
430
Header
0.03 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
Q8_0
263
F32
166
F16
1

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.