gemma-3-27b-it-qat-q4_0-unquantized · unsloth
gemma-3-27b-it-qat-q4_0-unquantized BF16
This file is exactly 54,027,964,480 bytes — 50.32 GiB / 54.03 GB at an effective 15.756 bits per weight. The nominal rate for BF16 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 2 file(s), summed
Get it
50.32 GiB · 2 files
llama.cpp
llama-cli -hf unsloth/gemma-3-27b-it-qat-GGUF:BF16
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/gemma-3-27b-it-qat-GGUF --include "BF16/gemma-3-27b-it-qat-BF16-*-of-*.gguf"
This quantization is split across 2 files totalling 50.32 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 2 required
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
50.32 GiB
54.03 GB
Effective bpw
15.756
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata