Krea-2-Raw · molbal

Krea-2-Raw Q5_1

This file is exactly 21,315,266,624 bytes — 19.85 GiB / 21.32 GB at an effective 13.301 bits per weight. The nominal rate for Q5_1 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

19.85 GiB · 2 files
llama.cpp
llama-cli -hf molbal/krea2-gguf:Q5_1

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

Hugging Face CLI
hf download molbal/krea2-gguf --include "krea2_raw_bf16-Q5_1.gguf"

This quantization is split across 2 files totalling 19.85 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
19.85 GiB
21.32 GB
Effective bpw
13.301
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata