gemma-3-12b-it-qat-q4_0-unquantized · unsloth
gemma-3-12b-it-qat-q4_0-unquantized IQ4_XS
This file is exactly 6,550,964,608 bytes — 6.10 GiB / 6.55 GB at an effective 4.300 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), summedFrom the file· 626 tensors parsed
Get it
6.10 GiB · 1 file
llama.cpp
llama-cli -hf unsloth/gemma-3-12b-it-qat-GGUF:IQ4_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download unsloth/gemma-3-12b-it-qat-GGUF gemma-3-12b-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
6.10 GiB
6.55 GB
Effective bpw
4.300
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
IQ4_XS
336
F32
289
Q6_K
1
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.