WAN2.2-14B-Rapid-AllInOne · DoorZekor

WAN2.2-14B-Rapid-AllInOne Q8_0

This file is exactly 17,652,508,416 bytes — 16.44 GiB / 17.65 GB at an effective 8.145 bits per weight. The nominal rate for Q8_0 is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 1303 tensors parsed

Get it

16.44 GiB · 1 file
llama.cpp
llama-cli -hf DoorZekor/WAN2.2-14B-Rapid-AllInOne-GGUF-NSFW-v10:Q8_0

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

Hugging Face CLI
hf download DoorZekor/WAN2.2-14B-Rapid-AllInOne-GGUF-NSFW-v10 wan2.2-i2v-rapid-aio-v10-nsfw-Q8_0.gguf
Direct download

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.

Repository →
Size
16.44 GiB
17.65 GB
Effective bpw
8.145
from real bytes ÷ params
Tensors
1303
Header
0.08 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F16
821
Q8_0
480
F32
2

A quantization label names a mixture, not a uniform precision. Attention and output tensors are routinely kept at higher precision than the label implies, which is exactly why the effective bits-per-weight above exceeds the nominal rate.