Kimiko-v2-13B · TheBloke
Kimiko-v2-13B Q3_K_M
This file is exactly 6,337,769,408 bytes — 5.90 GiB / 6.34 GB at an effective 3.895 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
5.90 GiB · 1 file
llama.cpp
llama-cli -hf TheBloke/Kimiko-v2-13B-GGUF:Q3_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download TheBloke/Kimiko-v2-13B-GGUF kimiko-v2-13b.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
5.90 GiB
6.34 GB
Effective bpw
3.895
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata