Model comparison

Wan2.2-TI2V-5B-Turbo vs Wan_2.1_ComfyUI_repackaged

At Q4_K_M, Wan2.2-TI2V-5B-Turbo is the smaller download — 3,437,927,136 bytes against 68,351,109,664.

From the file· summed bytes, KV per layer

Side by side

Wan2.2-TI2V-5B-TurboWan_2.1_ComfyUI_repackaged
Parameters5.0B
Architecturewanpig
Layers
Native context
Mixture of expertsnono
Quantizations published2248
Smallest quantization1.73 GiB4.25 GiB
Q4_K_M3.20 GiB63.66 GiB
Licenceapache-2.0apache-2.0

KV cache by context

the term that decides long-context viability
ContextWan2.2-TI2V-5B-TurboWan_2.1_ComfyUI_repackagedRatio
4,096
8,192
16,384
32,768
65,536
131,072