ideogram-4-fp8 · molbal
ideogram-4-fp8 Q5_1
This file is exactly 14,656,716,352 bytes — 13.65 GiB / 14.66 GB at an effective 12.633 bits per weight. The nominal rate for Q5_1 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
13.65 GiB · 2 files
llama.cpp
llama-cli -hf molbal/ideogram-4-gguf:Q5_1
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download molbal/ideogram-4-gguf --include "ideogram4-transformer-q5_1.gguf"
This quantization is split across 2 files totalling 13.65 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
13.65 GiB
14.66 GB
Effective bpw
12.633
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata