stable-diffusion-3.5-large Q8_0

This file is exactly 8,779,212,512 bytes — 8.18 GiB / 8.78 GB at an effective 8.622 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 923 tensors parsed

Get it

8.18 GiB · 1 file
llama.cpp
llama-cli -hf city96/stable-diffusion-3.5-large-gguf:Q8_0

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

Hugging Face CLI
hf download city96/stable-diffusion-3.5-large-gguf sd3.5_large-Q8_0.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
8.18 GiB
8.78 GB
Effective bpw
8.622
from real bytes ÷ params
Tensors
923
Header
0.07 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F16
546
Q8_0
377

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.