Wan2.2-VACE-Fun-A14B · QuantStack
Wan2.2-VACE-Fun-A14B Q6_K
This file is exactly 14,522,587,040 bytes — 13.53 GiB / 14.52 GB at an effective 6.701 bits per weight. The nominal rate for Q6_K is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summedFrom the file· 1331 tensors parsed
Get it
13.53 GiB · 1 file
llama.cpp
llama-cli -hf QuantStack/Wan2.2-VACE-Fun-A14B-GGUF:Q6_K
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download QuantStack/Wan2.2-VACE-Fun-A14B-GGUF LowNoise/Wan2.2-VACE-Fun-A14B-low-noise-Q6_K.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.
Size
13.53 GiB
14.52 GB
Effective bpw
6.701
from real bytes ÷ params
Tensors
1331
Header
0.08 MB
GGUF metadata
What this quantization actually contains
per-tensor types, parsed from the GGUF header
F32
836
Q6_K
489
BF16
6
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.