FLUX.2-dev · gguf-org

FLUX.2-dev IQ4_XS

This file is exactly 29,936,513,696 bytes — 27.88 GiB / 29.94 GB at an effective 7.432 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 2 file(s), summed

Get it

27.88 GiB · 2 files
llama.cpp
llama-cli -hf gguf-org/flux2-dev-gguf:IQ4_XS

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

Hugging Face CLI
hf download gguf-org/flux2-dev-gguf --include "cow-mistral3-small-iq4_xs.gguf"

This quantization is split across 2 files totalling 27.88 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 2 required

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
27.88 GiB
29.94 GB
Effective bpw
7.432
from real bytes ÷ params
Tensors
Header
GGUF metadata
FLUX.2-dev IQ4_XS — exact size and VRAM — ossmodeldb