Model comparison

lingbot-video-moe-30b-a3b vs Wan2.2-I2V-A14B

At Q4_K_M, Wan2.2-I2V-A14B is the smaller download — 9,651,728,896 bytes against 17,026,985,056.

From the file· summed bytes, KV per layer

Side by side

lingbot-video-moe-30b-a3bWan2.2-I2V-A14B
Parameters30.1B14.3B
Architecturewanwan
Layers
Native context
Mixture of expertsnono
Quantizations published230
Smallest quantization12.12 GiB4.94 GiB
Q4_K_M15.86 GiB8.99 GiB
Licenceotherapache-2.0

KV cache by context

the term that decides long-context viability
Contextlingbot-video-moe-30b-a3bWan2.2-I2V-A14BRatio
4,096
8,192
16,384
32,768
65,536
131,072