gemma-3-12b-it-qat-q4_0-unquantized Q6_K

This file is exactly 9,660,811,936 bytes — 9.00 GiB / 9.66 GB at an effective 6.341 bits per weight. The nominal rate for Q6_K 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

9.00 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/google_gemma-3-12b-it-qat-GGUF:Q6_K

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-Q6_K.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
9.00 GiB
9.66 GB
Effective bpw
6.341
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
Q6_K
337
F32
289

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.