datagemma-rig-27b-it IQ3_XS

This file is exactly 11,550,629,952 bytes — 10.76 GiB / 11.55 GB at an effective 3.394 bits per weight. The nominal rate for IQ3_XS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

10.76 GiB · 1 file
llama.cpp
llama-cli -hf bartowski/datagemma-rig-27b-it-GGUF:IQ3_XS

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

Hugging Face CLI
hf download bartowski/datagemma-rig-27b-it-GGUF datagemma-rig-27b-it-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
10.76 GiB
11.55 GB
Effective bpw
3.394
from real bytes ÷ params
Tensors
Header
GGUF metadata
datagemma-rig-27b-it IQ3_XS — exact size and VRAM — ossmodeldb