gemma-3-4b-it-qat-q4_0-unquantized Q8_0

This file is exactly 4,130,402,176 bytes — 3.85 GiB / 4.13 GB at an effective 7.684 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

3.85 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/gemma-3-4b-it-qat-GGUF:Q8_0

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

Hugging Face CLI
hf download unsloth/gemma-3-4b-it-qat-GGUF gemma-3-4b-it-qat-Q8_0.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
3.85 GiB
4.13 GB
Effective bpw
7.684
from real bytes ÷ params
Tensors
Header
GGUF metadata
gemma-3-4b-it-qat-q4_0-unquantized Q8_0 — exact size and VRAM — ossmodeldb