datagemma-rig-27b-it · legraphista
datagemma-rig-27b-it IQ2_S
This file is exactly 8,652,161,088 bytes — 8.06 GiB / 8.65 GB at an effective 2.542 bits per weight. The nominal rate for IQ2_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
8.06 GiB · 1 file
llama.cpp
llama-cli -hf legraphista/datagemma-rig-27b-it-IMat-GGUF:IQ2_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download legraphista/datagemma-rig-27b-it-IMat-GGUF datagemma-rig-27b-it.IQ2_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
8.06 GiB
8.65 GB
Effective bpw
2.542
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata