GLM-5.2-FP8-Uncensored · phaseonx11
GLM-5.2-FP8-Uncensored Q6_K
This file is exactly 618,583,923,488 bytes — 576.10 GiB / 618.58 GB at an effective 6.569 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 15 file(s), summed
Get it
576.10 GiB · 15 files
llama.cpp
llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-Q6_K-00001-of-00015.gguf"
This quantization is split across 15 files totalling 576.10 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 15 required
- glm52-Q6_K-00001-of-00015.gguf
- glm52-Q6_K-00002-of-00015.gguf
- glm52-Q6_K-00003-of-00015.gguf
- glm52-Q6_K-00004-of-00015.gguf
- glm52-Q6_K-00005-of-00015.gguf
- glm52-Q6_K-00006-of-00015.gguf
- glm52-Q6_K-00007-of-00015.gguf
- glm52-Q6_K-00008-of-00015.gguf
- glm52-Q6_K-00009-of-00015.gguf
- glm52-Q6_K-00010-of-00015.gguf
- glm52-Q6_K-00011-of-00015.gguf
- glm52-Q6_K-00012-of-00015.gguf
- glm52-Q6_K-00013-of-00015.gguf
- glm52-Q6_K-00014-of-00015.gguf
- glm52-Q6_K-00015-of-00015.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
576.10 GiB
618.58 GB
Effective bpw
6.569
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata