GLM-5.2-ABLITERATED-BF16 Q5_K_M

This file is exactly 534,072,139,936 bytes — 497.39 GiB / 534.07 GB at an effective 5.672 bits per weight. The nominal rate for Q5_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 11 file(s), summed

Get it

497.39 GiB · 11 files
llama.cpp
llama-cli -hf frz1/GLM-5.2-abliterated-GGUF:Q5_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 "Q5_K_M/GLM-5.2-abliterated-Q5_K_M-00001-of-00011.gguf"

This quantization is split across 11 files totalling 497.39 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 11 required

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
497.39 GiB
534.07 GB
Effective bpw
5.672
from real bytes ÷ params
Tensors
Header
GGUF metadata