FLUX.2-dev · unsloth

FLUX.2-dev Q3_K_M

This file is exactly 15,829,783,520 bytes — 14.74 GiB / 15.83 GB at an effective 3.930 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· 299 tensors parsed

Get it

14.74 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/FLUX.2-dev-GGUF:Q3_K_M

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download unsloth/FLUX.2-dev-GGUF flux2-dev-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.

Repository →
Size
14.74 GiB
15.83 GB
Effective bpw
3.930
from real bytes ÷ params
Tensors
299
Header
0.02 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
128
Q3_K
124
Q4_K
36
BF16
11

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.