translategemma-4b-it · mradermacher

translategemma-4b-it Q3_K_S

This file is exactly 1,937,379,840 bytes — 1.80 GiB / 1.94 GB at an effective 3.118 bits per weight. The nominal rate for Q3_K_S is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

1.80 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/translategemma-4b-it-GGUF:Q3_K_S

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

Hugging Face CLI
hf download mradermacher/translategemma-4b-it-GGUF translategemma-4b-it.Q3_K_S.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
1.80 GiB
1.94 GB
Effective bpw
3.118
from real bytes ÷ params
Tensors
Header
GGUF metadata
translategemma-4b-it Q3_K_S — exact size and VRAM — ossmodeldb