FLUX.2-klein-base-4B Q5_K_M

This file is exactly 3,073,368,640 bytes — 2.86 GiB / 3.07 GB at an effective 6.344 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.86 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/FLUX.2-klein-base-4B-GGUF:Q5_K_M

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-Q5_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.

Size
2.86 GiB
3.07 GB
Effective bpw
6.344
from real bytes ÷ params
Tensors
Header
GGUF metadata