Model comparison

Wan2.2-Fun-A14B-Control vs LTX-2

At Q4_K_M, Wan2.2-Fun-A14B-Control is the smaller download — 9,663,556,352 bytes against 12,840,118,752.

From the file· summed bytes, KV per layer

Side by side

Wan2.2-Fun-A14B-ControlLTX-2
Parameters14.3B18.9B
Architecturewanltxv
Layers
Native context
Mixture of expertsnono
Quantizations published2628
Smallest quantization4.95 GiB7.48 GiB
Q4_K_M9.00 GiB11.96 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
ContextWan2.2-Fun-A14B-ControlLTX-2Ratio
4,096
8,192
16,384
32,768
65,536
131,072