GLM-5.2-FP8-Uncensored · phaseonx11
GLM-5.2-FP8-Uncensored Q8_0
This file is exactly 800,777,319,456 bytes — 745.78 GiB / 800.78 GB at an effective 8.503 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.
From the file· 20 file(s), summed
Get it
745.78 GiB · 20 files
llama.cpp
llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:Q8_0
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-Q8_0-00001-of-00020.gguf"
This quantization is split across 20 files totalling 745.78 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 20 required
- glm52-Q8_0-00001-of-00020.gguf
- glm52-Q8_0-00002-of-00020.gguf
- glm52-Q8_0-00003-of-00020.gguf
- glm52-Q8_0-00004-of-00020.gguf
- glm52-Q8_0-00005-of-00020.gguf
- glm52-Q8_0-00006-of-00020.gguf
- glm52-Q8_0-00007-of-00020.gguf
- glm52-Q8_0-00008-of-00020.gguf
- glm52-Q8_0-00009-of-00020.gguf
- glm52-Q8_0-00010-of-00020.gguf
- glm52-Q8_0-00011-of-00020.gguf
- glm52-Q8_0-00012-of-00020.gguf
- glm52-Q8_0-00013-of-00020.gguf
- glm52-Q8_0-00014-of-00020.gguf
- glm52-Q8_0-00015-of-00020.gguf
- glm52-Q8_0-00016-of-00020.gguf
- glm52-Q8_0-00017-of-00020.gguf
- glm52-Q8_0-00018-of-00020.gguf
- glm52-Q8_0-00019-of-00020.gguf
- glm52-Q8_0-00020-of-00020.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
745.78 GiB
800.78 GB
Effective bpw
8.503
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata