WAN2.2-14B-Rapid-AllInOne · desirel

WAN2.2-14B-Rapid-AllInOne F16

This file is exactly 32,791,324,416 bytes — 30.54 GiB / 32.79 GB at an effective 15.131 bits per weight. The nominal rate for F16 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

30.54 GiB · 1 file
llama.cpp
llama-cli -hf desirel/WAN2.2-14B-Rapid-AllInOne-GGUF-NSFW-v10:F16

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

Hugging Face CLI
hf download desirel/WAN2.2-14B-Rapid-AllInOne-GGUF-NSFW-v10 wan2.2-i2v-rapid-aio-v10-nsfw-F16.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
30.54 GiB
32.79 GB
Effective bpw
15.131
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
1301
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.