stable-diffusion-3.5-medium Q5_1

This file is exactly 6,781,040,992 bytes — 6.32 GiB / 6.78 GB at an effective 21.966 bits per weight. The nominal rate for Q5_1 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 4 file(s), summed

Get it

6.32 GiB · 4 files
llama.cpp
llama-cli -hf second-state/stable-diffusion-3.5-medium-GGUF:Q5_1

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

Hugging Face CLI
hf download second-state/stable-diffusion-3.5-medium-GGUF --include "clip_g-Q5_1.gguf"

This quantization is split across 4 files totalling 6.32 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 4 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
6.32 GiB
6.78 GB
Effective bpw
21.966
from real bytes ÷ params
Tensors
Header
GGUF metadata