FLUX.2-klein-base-9B · unsloth

FLUX.2-klein-base-9B Q5_K_M

This file is exactly 7,018,699,040 bytes — 6.54 GiB / 7.02 GB at an effective 6.185 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), summedFrom the file· 201 tensors parsed

Get it

6.54 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/FLUX.2-klein-base-9B-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-9B-GGUF flux-2-klein-base-9b-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.

Repository →
Size
6.54 GiB
7.02 GB
Effective bpw
6.185
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
Q5_K
76
Q6_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.