MN-12B-Lyra-v4 · Lewdiculous
MN-12B-Lyra-v4 BF16
This file is exactly 24,504,279,488 bytes — 22.82 GiB / 24.50 GB at an effective 16.006 bits per weight. The nominal rate for BF16 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
22.82 GiB · 1 file
llama.cpp
llama-cli -hf Lewdiculous/MN-12B-Lyra-v4-GGUF-IQ-Imatrix:BF16
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download Lewdiculous/MN-12B-Lyra-v4-GGUF-IQ-Imatrix MN-12B-Lyra-v4-BF16.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
22.82 GiB
24.50 GB
Effective bpw
16.006
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata