gemma-4-12B-it-qat-q4_0-unquantized-heretic-empathy-ja I1-IQ4_XS

This file is exactly 6,635,257,056 bytes — 6.18 GiB / 6.64 GB at an effective 4.458 bits per weight. The nominal rate for I1-IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

6.18 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/gemma-4-12B-it-qat-q4_0-unquantized-heretic-empathy-ja-i1-GGUF:I1-IQ4_XS

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

Hugging Face CLI
hf download mradermacher/gemma-4-12B-it-qat-q4_0-unquantized-heretic-empathy-ja-i1-GGUF gemma-4-12B-it-qat-q4_0-unquantized-heretic-empathy-ja.i1-IQ4_XS.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
6.18 GiB
6.64 GB
Effective bpw
4.458
from real bytes ÷ params
Tensors
Header
GGUF metadata
gemma-4-12B-it-qat-q4_0-unquantized-heretic-empathy-ja I1-IQ4_XS — exact size and VRAM — ossmodeldb