Illustrious-xl-early-release-v0 · calcuis
Illustrious-xl-early-release-v0 Q3_K_M
This file is exactly 4,615,130,752 bytes — 4.30 GiB / 4.62 GB at an effective 14.380 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 4 file(s), summed
Get it
4.30 GiB · 4 files
llama.cpp
llama-cli -hf calcuis/illustrious:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download calcuis/illustrious --include "fast-illustrious-q3_k_m.gguf"
This quantization is split across 4 files totalling 4.30 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 4 required
- fast-illustrious-q3_k_m.gguf
- illustrious-q3_k_m.gguf
- illustrious_v110-q3_k_m.gguf
- illustrious_v90-q3_k_m.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.
Size
4.30 GiB
4.62 GB
Effective bpw
14.380
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata