Wan2.2-T2V-A14B · QuantStack

Wan2.2-T2V-A14B Q3_K_M

This file is exactly 7,174,468,096 bytes — 6.68 GiB / 7.17 GB at an effective 4.017 bits per weight. The nominal rate for Q3_K_M is lower; mixed-precision tensors make the real figure higher, always.

From the file· 1 file(s), summedFrom the file· 1095 tensors parsed

Get it

6.68 GiB · 1 file
llama.cpp
llama-cli -hf QuantStack/Wan2.2-T2V-A14B-GGUF:Q3_K_M

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

Hugging Face CLI
hf download QuantStack/Wan2.2-T2V-A14B-GGUF LowNoise/Wan2.2-T2V-A14B-LowNoise-Q3_K_M.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
6.68 GiB
7.17 GB
Effective bpw
4.017
from real bytes ÷ params
Tensors
1095
Header
0.07 MB
GGUF metadata

What this quantization actually contains

per-tensor types, parsed from the GGUF header
F16
694
Q3_K
280
Q4_K
118
Q5_K
2
F32
1

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.