translategemma-27b-it · mradermacher

translategemma-27b-it I1-IQ2_XS

This file is exactly 8,438,919,936 bytes — 7.86 GiB / 8.44 GB at an effective 2.341 bits per weight. The nominal rate for I1-IQ2_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

7.86 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/translategemma-27b-it-i1-GGUF:I1-IQ2_XS

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

Hugging Face CLI
hf download mradermacher/translategemma-27b-it-i1-GGUF translategemma-27b-it.i1-IQ2_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
7.86 GiB
8.44 GB
Effective bpw
2.341
from real bytes ÷ params
Tensors
Header
GGUF metadata
translategemma-27b-it I1-IQ2_XS — exact size and VRAM — ossmodeldb