Krea-2-Turbo · realrebelai

Krea-2-Turbo Q4_K_M

This file is exactly 7,259,460,832 bytes — 6.76 GiB / 7.26 GB at an effective 4.530 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 432 tensors parsed

Get it

6.76 GiB · 1 file
llama.cpp
llama-cli -hf realrebelai/KREA-2_GGUFs:Q4_K_M

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

Hugging Face CLI
hf download realrebelai/KREA-2_GGUFs BASE/Krea-2-Base-Q4_K_M.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
6.76 GiB
7.26 GB
Effective bpw
4.530
from real bytes ÷ params
Tensors
432
Header
0.03 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
Q4_K
264
F32
166
F16
2

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.