FLUX.2-klein-base-4B · unsloth
FLUX.2-klein-base-4B Q6_K
This file is exactly 3,409,273,408 bytes — 3.18 GiB / 3.41 GB at an effective 7.037 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
3.18 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/FLUX.2-klein-base-4B-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/FLUX.2-klein-base-4B-GGUF flux-2-klein-base-4b-Q6_K.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.
Size
3.18 GiB
3.41 GB
Effective bpw
7.037
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata