FLUX.2-klein-base-9B · unsloth
FLUX.2-klein-base-9B Q3_K_M
This file is exactly 4,769,503,520 bytes — 4.44 GiB / 4.77 GB at an effective 4.203 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summedFrom the file· 201 tensors parsed
Get it
4.44 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/FLUX.2-klein-base-9B-GGUF:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/FLUX.2-klein-base-9B-GGUF flux-2-klein-base-9b-Q3_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
4.44 GiB
4.77 GB
Effective bpw
4.203
from real bytes ÷ params
Tensors
201
Header
0.01 MB
GGUF metadata
What this quantization actually contains
per-tensor types, parsed from the GGUF header
F32
80
Q3_K
76
Q4_K
36
BF16
9
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.