Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated · mradermacher
Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated I1-IQ3_S
This file is exactly 21,325,598,112 bytes — 19.86 GiB / 21.33 GB at an effective 3.473 bits per weight. The nominal rate for I1-IQ3_S is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
19.86 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated-i1-GGUF:I1-IQ3_S
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download mradermacher/Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated-i1-GGUF Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated.i1-IQ3_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
19.86 GiB
21.33 GB
Effective bpw
3.473
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata