MN-26B-Oblivion-Uncensored IQ3_M

This file is exactly 12,485,164,192 bytes — 11.63 GiB / 12.49 GB at an effective 3.901 bits per weight. The nominal rate for IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

11.63 GiB · 1 file
llama.cpp
llama-cli -hf DavidAU/MN-Oblivion-26B-UNCENSORED-NEO-Imatrix-GGUF:IQ3_M

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

Hugging Face CLI
hf download DavidAU/MN-Oblivion-26B-UNCENSORED-NEO-Imatrix-GGUF MN-Oblivion-26B-UNCENSORED-HITOP-IQ3_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
11.63 GiB
12.49 GB
Effective bpw
3.901
from real bytes ÷ params
Tensors
Header
GGUF metadata