Forgotten-Safeword-70B-3.6 IQ2_XXS

This file is exactly 19,097,398,464 bytes — 17.79 GiB / 19.10 GB at an effective 2.165 bits per weight. The nominal rate for IQ2_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

17.79 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/ReadyArt_Forgotten-Safeword-70B-3.6-GGUF:IQ2_XXS

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

Hugging Face CLI
hf download bartowski/ReadyArt_Forgotten-Safeword-70B-3.6-GGUF ReadyArt_Forgotten-Safeword-70B-3.6-IQ2_XXS.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
17.79 GiB
19.10 GB
Effective bpw
2.165
from real bytes ÷ params
Tensors
Header
GGUF metadata