GLM-5.2-FP8-Uncensored · phaseonx11
GLM-5.2-FP8-Uncensored Q4_K_M
This file is exactly 454,552,363,264 bytes — 423.33 GiB / 454.55 GB at an effective 4.827 bits per weight. The nominal rate for Q4_K_M is lower; mixed-precision tensors make the real figure higher, always.
From the file· 11 file(s), summed
Get it
423.33 GiB · 11 files
llama.cpp
llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:Q4_K_M
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-Q4_K_M-00001-of-00011.gguf"
This quantization is split across 11 files totalling 423.33 GiB. You need every part — the first is not a smaller version of the model.
Direct downloads — all 11 required
- glm52-Q4_K_M-00001-of-00011.gguf
- glm52-Q4_K_M-00002-of-00011.gguf
- glm52-Q4_K_M-00003-of-00011.gguf
- glm52-Q4_K_M-00004-of-00011.gguf
- glm52-Q4_K_M-00005-of-00011.gguf
- glm52-Q4_K_M-00006-of-00011.gguf
- glm52-Q4_K_M-00007-of-00011.gguf
- glm52-Q4_K_M-00008-of-00011.gguf
- glm52-Q4_K_M-00009-of-00011.gguf
- glm52-Q4_K_M-00010-of-00011.gguf
- glm52-Q4_K_M-00011-of-00011.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
423.33 GiB
454.55 GB
Effective bpw
4.827
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata