Model comparison

granite-4.0-1b vs Wan2.1-T2V-1.3B

At Q4_K_M, Wan2.1-T2V-1.3B is the smaller download — 982,716,640 bytes against 1,023,645,440.

From the file· summed bytes, KV per layer

Side by side

granite-4.0-1bWan2.1-T2V-1.3B
Parameters1.6B1.4B
Architecturegraniteqwen35
Layers40
Native context131,072
Mixture of expertsnono
Quantizations published3531
Smallest quantization0.44 GiB0.61 GiB
Q4_K_M0.95 GiB0.92 GiB
Licenceapache-2.0

KV cache by context

the term that decides long-context viability
Contextgranite-4.0-1bWan2.1-T2V-1.3BRatio
4,0960.31 GiB
8,1920.63 GiB
16,3841.25 GiB
32,7682.50 GiB
65,5365.00 GiB
131,07210.00 GiB