Webs-Sejong-31B-v2 · mradermacher
Webs-Sejong-31B-v2 I1-IQ2_XS
This file is exactly 9,530,359,104 bytes — 8.88 GiB / 9.53 GB at an effective 2.484 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
8.88 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Webs-Sejong-31B-v2-i1-GGUF:I1-IQ2_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Webs-Sejong-31B-v2-i1-GGUF Webs-Sejong-31B-v2.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
8.88 GiB
9.53 GB
Effective bpw
2.484
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata