Model comparison

WAN2.2-14B-Rapid-AllInOne vs MiniMax-H3

At Q4_K_M, WAN2.2-14B-Rapid-AllInOne is the smaller download — 10,849,052,416 bytes against 14,576,977,960.

From the file· summed bytes, KV per layer

Side by side

WAN2.2-14B-Rapid-AllInOneMiniMax-H3
Parameters17.3B33.1B
Architecturewanqwen3vl
Layers
Native context
Mixture of expertsnono
Quantizations published8222
Smallest quantization5.59 GiB10.60 GiB
Q4_K_M10.10 GiB13.58 GiB
Licenceother

KV cache by context

the term that decides long-context viability
ContextWAN2.2-14B-Rapid-AllInOneMiniMax-H3Ratio
4,096
8,192
16,384
32,768
65,536
131,072