Model comparison

SCAIL-2 vs LTX-2

At Q4_K_M, SCAIL-2 is the smaller download — 10,862,812,832 bytes against 12,840,118,752.

From the file· summed bytes, KV per layer

Side by side

SCAIL-2LTX-2
Parameters16.4B18.9B
Architecturewanltxv
Layers
Native context
Mixture of expertsnono
Quantizations published2628
Smallest quantization5.61 GiB7.48 GiB
Q4_K_M10.12 GiB11.96 GiB
Licencemit

KV cache by context

the term that decides long-context viability
ContextSCAIL-2LTX-2Ratio
4,096
8,192
16,384
32,768
65,536
131,072