Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated I1-Q4_K_M

This file is exactly 29,702,759,968 bytes — 27.66 GiB / 29.70 GB at an effective 4.837 bits per weight. The nominal rate for I1-Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summed

Get it

27.66 GiB · 1 file
llama.cpp
llama-cli -hf mradermacher/Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated-i1-GGUF:I1-Q4_K_M

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-Q4_K_M.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
27.66 GiB
29.70 GB
Effective bpw
4.837
from real bytes ÷ params
Tensors
Header
GGUF metadata
Huihui-Kimi-Linear-48B-A3B-Instruct-abliterated I1-Q4_K_M — exact size and VRAM — ossmodeldb