ideogram-4-fp8 · rectangleworm

ideogram-4-fp8 Q6_K

This file is exactly 8,037,768,992 bytes — 7.49 GiB / 8.04 GB at an effective 6.928 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

7.49 GiB · 1 file
llama.cpp
llama-cli -hf rectangleworm/ideogram-4-gguf:Q6_K

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

Hugging Face CLI
hf download rectangleworm/ideogram-4-gguf diffusion/cond/ideogram4-Q6_K.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
7.49 GiB
8.04 GB
Effective bpw
6.928
from real bytes ÷ params
Tensors
Header
GGUF metadata
ideogram-4-fp8 Q6_K — exact size and VRAM — ossmodeldb