GLM-5.2-ABLITERATED-BF16 Q4_K_M

This file is exactly 454,660,890,496 bytes — 423.44 GiB / 454.66 GB at an effective 4.828 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 10 file(s), summed

Get it

423.44 GiB · 10 files
llama.cpp
llama-cli -hf frz1/GLM-5.2-abliterated-GGUF:Q4_K_M

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download frz1/GLM-5.2-abliterated-GGUF --include "Q4_K_M/GLM-5.2-abliterated-Q4_K_M-00001-of-00010.gguf"

This quantization is split across 10 files totalling 423.44 GiB. You need every part — the first is not a smaller version of the model.

Size
423.44 GiB
454.66 GB
Effective bpw
4.828
from real bytes ÷ params
Tensors
Header
GGUF metadata