GLM-5.2-FP8-Uncensored IQ3_XXS

This file is exactly 366,220,601,376 bytes — 341.07 GiB / 366.22 GB at an effective 3.889 bits per weight. The nominal rate for IQ3_XXS is lower; mixed-precision tensors make the real figure higher, always.

From the file· 9 file(s), summed

Get it

341.07 GiB · 9 files
llama.cpp
llama-cli -hf phaseonx11/GLM-5.2-Uncensored-GGUF:IQ3_XXS

Downloads and runs in one step, resolving the quantization by name.

Hugging Face CLI
hf download phaseonx11/GLM-5.2-Uncensored-GGUF --include "glm52-IQ3_XXS-*-of-*.gguf"

This quantization is split across 9 files totalling 341.07 GiB. You need every part — the first is not a smaller version of the model.

Direct downloads — all 9 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
341.07 GiB
366.22 GB
Effective bpw
3.889
from real bytes ÷ params
Tensors
Header
GGUF metadata
GLM-5.2-FP8-Uncensored IQ3_XXS — exact size and VRAM — ossmodeldb