QoolKid-14b · mradermacher
QoolKid-14b I1-Q3_K_M
This file is exactly 7,321,314,272 bytes — 6.82 GiB / 7.32 GB at an effective 3.966 bits per weight. The nominal rate for I1-Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
6.82 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/QoolKid-14b-i1-GGUF:I1-Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/QoolKid-14b-i1-GGUF QoolKid-14b.i1-Q3_K_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
6.82 GiB
7.32 GB
Effective bpw
3.966
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata