Krea-2-Raw · molbal
Krea-2-Raw Q4_1
This file is exactly 18,190,444,608 bytes — 16.94 GiB / 18.19 GB at an effective 11.351 bits per weight. The nominal rate for Q4_1 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
16.94 GiB · 2 files
llama.cpp
llama-cli -hf molbal/krea2-gguf:Q4_1
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download molbal/krea2-gguf --include "krea2_raw_bf16-Q4_1.gguf"
This quantization is split across 2 files totalling 16.94 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.
Size
16.94 GiB
18.19 GB
Effective bpw
11.351
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata