MN-12B-Lyra-v4 · bartowski
MN-12B-Lyra-v4 IQ4_XS
This file is exactly 6,742,713,056 bytes — 6.28 GiB / 6.74 GB at an effective 4.404 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
6.28 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/MN-12B-Lyra-v4-GGUF:IQ4_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download bartowski/MN-12B-Lyra-v4-GGUF MN-12B-Lyra-v4-IQ4_XS.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
6.28 GiB
6.74 GB
Effective bpw
4.404
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata