Gemma-4-31B-Animus-V15.0 · Darkhn-Quants-4

Gemma-4-31B-Animus-V15.0 Q4_K_M

This file is exactly 18,687,064,256 bytes — 17.40 GiB / 18.69 GB at an effective 4.574 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

17.40 GiB · 1 file
llama.cpp
llama-cli -hf Darkhn-Quants-4/Gemma-4-31B-Animus-V15.0-GGUF:Q4_K_M

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

Hugging Face CLI
hf download Darkhn-Quants-4/Gemma-4-31B-Animus-V15.0-GGUF Gemma-4-31B-Animus-V15.0-Imat-Q4_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
17.40 GiB
18.69 GB
Effective bpw
4.574
from real bytes ÷ params
Tensors
Header
GGUF metadata
Gemma-4-31B-Animus-V15.0 Q4_K_M — exact size and VRAM — ossmodeldb