Dark-Scarlett-v1.0-35B-A3B · ReadyArt
Dark-Scarlett-v1.0-35B-A3B Q8_0
This file is exactly 38,593,496,192 bytes — 35.94 GiB / 38.59 GB at an effective 8.696 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
35.94 GiB · 1 file
llama.cpp
llama-cli -hf ReadyArt/Dark-Scarlett-v1.0-35B-A3B-GGUF:Q8_0
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download ReadyArt/Dark-Scarlett-v1.0-35B-A3B-GGUF Dark-Scarlett-v1.0-35B-A3B-Q8_0.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
35.94 GiB
38.59 GB
Effective bpw
8.696
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata