ideogram-4-fp8 · rectangleworm
ideogram-4-fp8 Q5_K_M
This file is exactly 5,851,114,336 bytes — 5.45 GiB / 5.85 GB at an effective 5.043 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
5.45 GiB · 1 file
llama.cpp
llama-cli -hf rectangleworm/ideogram-4-gguf:Q5_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download rectangleworm/ideogram-4-gguf text_encoder/Qwen3-VL-8B-Q5_K_M.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
5.45 GiB
5.85 GB
Effective bpw
5.043
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata