translategemma-12b-it · mradermacher

translategemma-12b-it I1-IQ3_XS

This file is exactly 5,206,181,888 bytes — 4.85 GiB / 5.21 GB at an effective 3.157 bits per weight. The nominal rate for I1-IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

4.85 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/translategemma-12b-it-i1-GGUF:I1-IQ3_XS

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

Hugging Face CLI
hf download mradermacher/translategemma-12b-it-i1-GGUF translategemma-12b-it.i1-IQ3_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
4.85 GiB
5.21 GB
Effective bpw
3.157
from real bytes ÷ params
Tensors
Header
GGUF metadata
translategemma-12b-it I1-IQ3_XS — exact size and VRAM — ossmodeldb