HiDream-I1-Full · city96

HiDream-I1-Full Q8_0

This file is exactly 18,689,407,552 bytes — 17.41 GiB / 18.69 GB at an effective 8.741 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), summed

Get it

17.41 GiB · 1 file

llama.cpp

llama-cli -hf city96/HiDream-I1-Full-gguf:Q8_0

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

Hugging Face CLI

hf download city96/HiDream-I1-Full-gguf hidream-i1-full-Q8_0.gguf

Direct download

hidream-i1-full-Q8_0.gguf

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

17.41 GiB

18.69 GB

Effective bpw

8.741

from real bytes ÷ params

Tensors

—

Header

—

GGUF metadata