datagemma-rag-27b-it · legraphista
datagemma-rag-27b-it IQ4_NL
This file is exactly 15,628,378,176 bytes — 14.56 GiB / 15.63 GB at an effective 4.592 bits per weight. The nominal rate for IQ4_NL is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
14.56 GiB · 1 file
llama.cpp
llama-cli -hf legraphista/datagemma-rag-27b-it-IMat-GGUF:IQ4_NL
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download legraphista/datagemma-rag-27b-it-IMat-GGUF datagemma-rag-27b-it.IQ4_NL.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
14.56 GiB
15.63 GB
Effective bpw
4.592
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata