gemma-3-4b-it-qat-q4_0-unquantized IQ4_XS

This file is exactly 2,263,242,144 bytes — 2.11 GiB / 2.26 GB at an effective 4.211 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

2.11 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/google_gemma-3-4b-it-qat-GGUF:IQ4_XS

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

Hugging Face CLI
hf download bartowski/google_gemma-3-4b-it-qat-GGUF google_gemma-3-4b-it-qat-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
2.11 GiB
2.26 GB
Effective bpw
4.211
from real bytes ÷ params
Tensors
Header
GGUF metadata