gemma-3-12b-it-qat-q4_0-unquantized IQ3_M

This file is exactly 5,655,722,656 bytes — 5.27 GiB / 5.66 GB at an effective 3.712 bits per weight. The nominal rate for IQ3_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

5.27 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/google_gemma-3-12b-it-qat-GGUF:IQ3_M

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

Hugging Face CLI
hf download bartowski/google_gemma-3-12b-it-qat-GGUF google_gemma-3-12b-it-qat-IQ3_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
5.27 GiB
5.66 GB
Effective bpw
3.712
from real bytes ÷ params
Tensors
Header
GGUF metadata