GLM-5.2-FP8-Uncensored · phaseonx11
GLM-5.2-FP8-Uncensored IQ4_XS
This file is exactly 400,955,277,504 bytes — 373.42 GiB / 400.96 GB at an effective 4.258 bits per weight. The nominal rate for IQ4_XS is lower; mixed-precision tensors make the real figure higher, always.
From the file· 10 file(s), summed
Get it
373.42 GiB · 10 files
llama.cpp
llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:IQ4_XS
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-IQ4_XS-00001-of-00010.gguf"
This quantization is split across 10 files totalling 373.42 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 10 required
- glm52-IQ4_XS-00001-of-00010.gguf
- glm52-IQ4_XS-00002-of-00010.gguf
- glm52-IQ4_XS-00003-of-00010.gguf
- glm52-IQ4_XS-00004-of-00010.gguf
- glm52-IQ4_XS-00005-of-00010.gguf
- glm52-IQ4_XS-00006-of-00010.gguf
- glm52-IQ4_XS-00007-of-00010.gguf
- glm52-IQ4_XS-00008-of-00010.gguf
- glm52-IQ4_XS-00009-of-00010.gguf
- glm52-IQ4_XS-00010-of-00010.gguf
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
373.42 GiB
400.96 GB
Effective bpw
4.258
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata