gemma-3-12b-it-qat-q4_0-unquantized · bartowski

gemma-3-12b-it-qat-q4_0-unquantized Q3_K_M

This file is exactly 6,008,818,336 bytes — 5.60 GiB / 6.01 GB at an effective 3.944 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), summedFrom the file· 626 tensors parsed

Get it

5.60 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/google_gemma-3-12b-it-qat-GGUF:Q3_K_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-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.

Repository →
Size
5.60 GiB
6.01 GB
Effective bpw
3.944
from real bytes ÷ params
Tensors
626
Header
6.55 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F32
289
Q3_K
192
Q4_K
139
Q5_K
5
Q6_K
1

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.